semantic-crawler 0.0.2 → 0.0.3
Sign up to get free protection for your applications and to get access to all the features.
- data/README.rdoc +17 -6
- data/Rakefile +2 -4
- data/lib/semantic_crawler.rb +25 -2
- data/lib/semantic_crawler/factbook.rb +11 -0
- data/lib/semantic_crawler/factbook/country.rb +15 -5
- data/lib/semantic_crawler/freebase.rb +4 -0
- data/lib/semantic_crawler/freebase/country.rb +5 -0
- data/lib/semantic_crawler/freebase/crawler.rb +1 -0
- data/lib/semantic_crawler/freebase/entity.rb +1 -0
- data/lib/semantic_crawler/gdacs.rb +6 -0
- data/lib/semantic_crawler/gdacs/feed.rb +100 -0
- data/lib/semantic_crawler/gdacs/feed_item.rb +172 -0
- data/lib/semantic_crawler/gdacs/resource.rb +66 -0
- data/lib/semantic_crawler/linked_geo_data.rb +5 -0
- data/lib/semantic_crawler/linked_geo_data/relevant_node.rb +13 -0
- data/lib/semantic_crawler/version.rb +3 -1
- data/test/dummy/log/test.log +4802 -0
- data/test/factbook_test.rb +1 -1
- data/test/gdacs_test.rb +80 -0
- metadata +37 -27
data/test/factbook_test.rb
CHANGED
@@ -8,7 +8,7 @@ class FactbookTest < ActiveSupport::TestCase
|
|
8
8
|
|
9
9
|
test "init austria country information" do
|
10
10
|
austria = SemanticCrawler::Factbook::Country.new("Austria")
|
11
|
-
assert austria.country_name.eql?("
|
11
|
+
assert austria.country_name.eql?("Austria")
|
12
12
|
assert austria.url.eql?("http://www4.wiwiss.fu-berlin.de/factbook/data/austria")
|
13
13
|
end
|
14
14
|
|
data/test/gdacs_test.rb
ADDED
@@ -0,0 +1,80 @@
|
|
1
|
+
require 'test_helper'
|
2
|
+
require 'pp'
|
3
|
+
|
4
|
+
class GdacsTest < ActiveSupport::TestCase
|
5
|
+
test "truth" do
|
6
|
+
assert_kind_of Module, SemanticCrawler
|
7
|
+
end
|
8
|
+
|
9
|
+
test "init gdacs feed" do
|
10
|
+
feed = SemanticCrawler::Gdacs::Feed.new
|
11
|
+
assert !feed.url.nil?
|
12
|
+
end
|
13
|
+
|
14
|
+
test "get channel title" do
|
15
|
+
feed = SemanticCrawler::Gdacs::Feed.new
|
16
|
+
assert !feed.title.nil?
|
17
|
+
end
|
18
|
+
|
19
|
+
test "get channel description" do
|
20
|
+
feed = SemanticCrawler::Gdacs::Feed.new
|
21
|
+
assert !feed.description.nil?
|
22
|
+
end
|
23
|
+
|
24
|
+
test "get channel pubDate" do
|
25
|
+
feed = SemanticCrawler::Gdacs::Feed.new
|
26
|
+
assert !feed.pubDate.nil?
|
27
|
+
end
|
28
|
+
|
29
|
+
test "get channel webMaster" do
|
30
|
+
feed = SemanticCrawler::Gdacs::Feed.new
|
31
|
+
assert feed.webMaster.to_s.include?("@")
|
32
|
+
end
|
33
|
+
|
34
|
+
test "get channel managingEditor" do
|
35
|
+
feed = SemanticCrawler::Gdacs::Feed.new
|
36
|
+
assert feed.managingEditor.to_s.include?("@")
|
37
|
+
end
|
38
|
+
|
39
|
+
test "get channel atom:link" do
|
40
|
+
feed = SemanticCrawler::Gdacs::Feed.new
|
41
|
+
assert feed.atom_link.to_s.start_with?("http")
|
42
|
+
end
|
43
|
+
|
44
|
+
test "get channel item(s)" do
|
45
|
+
feed = SemanticCrawler::Gdacs::Feed.new
|
46
|
+
items = feed.items
|
47
|
+
assert !items.nil?
|
48
|
+
items.each do |item|
|
49
|
+
assert !item.title.nil?
|
50
|
+
assert !item.description.nil?
|
51
|
+
assert !item.link.nil?
|
52
|
+
assert !item.pubDate.nil?
|
53
|
+
assert !item.fromdate.nil?
|
54
|
+
assert !item.todate.nil?
|
55
|
+
assert !item.subject.nil?
|
56
|
+
assert !item.guid.nil?
|
57
|
+
assert !item.latitude.nil?
|
58
|
+
assert !item.longitude.nil?
|
59
|
+
assert !item.version.nil?
|
60
|
+
assert !item.eventtype.nil?
|
61
|
+
assert !item.alertlevel.nil?
|
62
|
+
assert !item.eventname.nil?
|
63
|
+
assert !item.eventid.nil?
|
64
|
+
assert !item.episodeid.nil?
|
65
|
+
assert !item.severity.nil?
|
66
|
+
assert !item.population.nil?
|
67
|
+
assert !item.vulnerability.nil?
|
68
|
+
assert !item.country.nil?
|
69
|
+
assert !item.iso3.nil?
|
70
|
+
assert !item.glide.nil?
|
71
|
+
resources = item.resources
|
72
|
+
resources.each do |resource|
|
73
|
+
assert !resource.title.nil?
|
74
|
+
assert !resource.url.nil?
|
75
|
+
assert !resource.type.nil?
|
76
|
+
end
|
77
|
+
end
|
78
|
+
end
|
79
|
+
|
80
|
+
end
|
metadata
CHANGED
@@ -1,13 +1,13 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: semantic-crawler
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
hash:
|
4
|
+
hash: 25
|
5
5
|
prerelease:
|
6
6
|
segments:
|
7
7
|
- 0
|
8
8
|
- 0
|
9
|
-
-
|
10
|
-
version: 0.0.
|
9
|
+
- 3
|
10
|
+
version: 0.0.3
|
11
11
|
platform: ruby
|
12
12
|
authors:
|
13
13
|
- Alex Oberhauser
|
@@ -15,12 +15,13 @@ autorequire:
|
|
15
15
|
bindir: bin
|
16
16
|
cert_chain: []
|
17
17
|
|
18
|
-
date: 2012-03-
|
18
|
+
date: 2012-03-26 00:00:00 Z
|
19
19
|
dependencies:
|
20
20
|
- !ruby/object:Gem::Dependency
|
21
|
-
|
21
|
+
type: :runtime
|
22
|
+
name: httparty
|
22
23
|
prerelease: false
|
23
|
-
|
24
|
+
version_requirements: &id001 !ruby/object:Gem::Requirement
|
24
25
|
none: false
|
25
26
|
requirements:
|
26
27
|
- - ">="
|
@@ -29,12 +30,12 @@ dependencies:
|
|
29
30
|
segments:
|
30
31
|
- 0
|
31
32
|
version: "0"
|
32
|
-
|
33
|
-
version_requirements: *id001
|
33
|
+
requirement: *id001
|
34
34
|
- !ruby/object:Gem::Dependency
|
35
|
-
|
35
|
+
type: :runtime
|
36
|
+
name: json
|
36
37
|
prerelease: false
|
37
|
-
|
38
|
+
version_requirements: &id002 !ruby/object:Gem::Requirement
|
38
39
|
none: false
|
39
40
|
requirements:
|
40
41
|
- - ">="
|
@@ -43,12 +44,12 @@ dependencies:
|
|
43
44
|
segments:
|
44
45
|
- 0
|
45
46
|
version: "0"
|
46
|
-
|
47
|
-
version_requirements: *id002
|
47
|
+
requirement: *id002
|
48
48
|
- !ruby/object:Gem::Dependency
|
49
|
-
|
49
|
+
type: :runtime
|
50
|
+
name: nokogiri
|
50
51
|
prerelease: false
|
51
|
-
|
52
|
+
version_requirements: &id003 !ruby/object:Gem::Requirement
|
52
53
|
none: false
|
53
54
|
requirements:
|
54
55
|
- - ">="
|
@@ -57,12 +58,12 @@ dependencies:
|
|
57
58
|
segments:
|
58
59
|
- 0
|
59
60
|
version: "0"
|
60
|
-
|
61
|
-
version_requirements: *id003
|
61
|
+
requirement: *id003
|
62
62
|
- !ruby/object:Gem::Dependency
|
63
|
-
|
63
|
+
type: :development
|
64
|
+
name: yard
|
64
65
|
prerelease: false
|
65
|
-
|
66
|
+
version_requirements: &id004 !ruby/object:Gem::Requirement
|
66
67
|
none: false
|
67
68
|
requirements:
|
68
69
|
- - ">="
|
@@ -71,12 +72,12 @@ dependencies:
|
|
71
72
|
segments:
|
72
73
|
- 0
|
73
74
|
version: "0"
|
74
|
-
|
75
|
-
version_requirements: *id004
|
75
|
+
requirement: *id004
|
76
76
|
- !ruby/object:Gem::Dependency
|
77
|
+
type: :development
|
77
78
|
name: rails
|
78
79
|
prerelease: false
|
79
|
-
|
80
|
+
version_requirements: &id005 !ruby/object:Gem::Requirement
|
80
81
|
none: false
|
81
82
|
requirements:
|
82
83
|
- - ~>
|
@@ -87,12 +88,12 @@ dependencies:
|
|
87
88
|
- 2
|
88
89
|
- 2
|
89
90
|
version: 3.2.2
|
90
|
-
|
91
|
-
version_requirements: *id005
|
91
|
+
requirement: *id005
|
92
92
|
- !ruby/object:Gem::Dependency
|
93
|
+
type: :development
|
93
94
|
name: sqlite3
|
94
95
|
prerelease: false
|
95
|
-
|
96
|
+
version_requirements: &id006 !ruby/object:Gem::Requirement
|
96
97
|
none: false
|
97
98
|
requirements:
|
98
99
|
- - ">="
|
@@ -101,9 +102,8 @@ dependencies:
|
|
101
102
|
segments:
|
102
103
|
- 0
|
103
104
|
version: "0"
|
104
|
-
|
105
|
-
|
106
|
-
description: SemanticCrawler is a ruby library that encapsulates data gathering from different sources.
|
105
|
+
requirement: *id006
|
106
|
+
description: SemanticCrawler is a ruby library that encapsulates data gathering from different sources. Currently country information from Factbook and crisis information from GDACS.org are supported.
|
107
107
|
email:
|
108
108
|
- alex.oberhauser@sigimera.org
|
109
109
|
executables: []
|
@@ -119,10 +119,19 @@ files:
|
|
119
119
|
- lib/semantic_crawler/freebase/crawler.rb
|
120
120
|
- lib/semantic_crawler/freebase/entity.rb
|
121
121
|
- lib/semantic_crawler/factbook/country.rb
|
122
|
+
- lib/semantic_crawler/freebase.rb
|
123
|
+
- lib/semantic_crawler/factbook.rb
|
124
|
+
- lib/semantic_crawler/gdacs.rb
|
122
125
|
- lib/semantic_crawler/version.rb
|
126
|
+
- lib/semantic_crawler/gdacs/resource.rb
|
127
|
+
- lib/semantic_crawler/gdacs/feed.rb
|
128
|
+
- lib/semantic_crawler/gdacs/feed_item.rb
|
129
|
+
- lib/semantic_crawler/linked_geo_data/relevant_node.rb
|
130
|
+
- lib/semantic_crawler/linked_geo_data.rb
|
123
131
|
- MIT-LICENSE
|
124
132
|
- Rakefile
|
125
133
|
- README.rdoc
|
134
|
+
- test/gdacs_test.rb
|
126
135
|
- test/test_helper.rb
|
127
136
|
- test/factbook_test.rb
|
128
137
|
- test/semantic_crawler_test.rb
|
@@ -192,6 +201,7 @@ signing_key:
|
|
192
201
|
specification_version: 3
|
193
202
|
summary: SemanticCrawler is a ruby library that encapsulates data gathering from different sources.
|
194
203
|
test_files:
|
204
|
+
- test/gdacs_test.rb
|
195
205
|
- test/test_helper.rb
|
196
206
|
- test/factbook_test.rb
|
197
207
|
- test/semantic_crawler_test.rb
|