semantic-crawler 0.5.0 → 0.6.0
Sign up to get free protection for your applications and to get access to all the features.
- data/README.rdoc +3 -3
- data/lib/semantic_crawler.rb +1 -0
- data/lib/semantic_crawler/factbook/country.rb +1 -1
- data/lib/semantic_crawler/gdacs/feed.rb +3 -3
- data/lib/semantic_crawler/gdacs/feed_item.rb +26 -1
- data/lib/semantic_crawler/gdacs/kml_file.rb +55 -0
- data/lib/semantic_crawler/version.rb +1 -1
- data/semantic_crawler.gemspec +1 -1
- data/spec/gdacs_spec.rb +13 -0
- data/spec/linked_geo_data_spec.rb +3 -3
- metadata +37 -35
- data/exploitation/freebase.rb +0 -13
data/README.rdoc
CHANGED
@@ -134,8 +134,8 @@ Freebase.com country information:
|
|
134
134
|
|
135
135
|
== Tested with
|
136
136
|
|
137
|
-
* Ruby 1.8.7-p358 and Rails 3.2
|
138
|
-
* Ruby 1.9.3-p125 and Rails 3.2
|
137
|
+
* Ruby 1.8.7-p358 and Rails 3.2
|
138
|
+
* Ruby 1.9.3-p125 and Rails 3.2
|
139
139
|
|
140
140
|
|
141
141
|
== Additional Links
|
@@ -156,6 +156,6 @@ published under MIT license.
|
|
156
156
|
== Warranty
|
157
157
|
|
158
158
|
This software is provided "as is" and without any express or implied
|
159
|
-
warranties, including, without limitation, the implied warranties of
|
159
|
+
warranties, including, without limitation, the implied warranties of
|
160
160
|
merchantibility and fitness for a particular purpose.
|
161
161
|
|
data/lib/semantic_crawler.rb
CHANGED
@@ -33,6 +33,7 @@ require "semantic_crawler/gdacs/feed_item.rb"
|
|
33
33
|
require "semantic_crawler/gdacs/resource.rb"
|
34
34
|
require "semantic_crawler/gdacs/emergency_feed.rb"
|
35
35
|
require "semantic_crawler/gdacs/emergency_feed_item.rb"
|
36
|
+
require "semantic_crawler/gdacs/kml_file.rb"
|
36
37
|
|
37
38
|
# DBPedia - module: Dbpedia
|
38
39
|
require "semantic_crawler/dbpedia"
|
@@ -17,13 +17,13 @@ module SemanticCrawler
|
|
17
17
|
}
|
18
18
|
|
19
19
|
# The gdacs.org RSS feed URL. (default:
|
20
|
-
# http://
|
20
|
+
# http://www.gdacs.org/xml/rss.xml)
|
21
21
|
attr_reader :url
|
22
22
|
|
23
23
|
# Initializes the gdacs.org feed URL. If not specified the default
|
24
|
-
# URL (http://
|
24
|
+
# URL (http://www.gdacs.org/xml/rss.xml) is used. Normally the
|
25
25
|
# feed URL should not be changed.
|
26
|
-
def initialize(new_url = "http://
|
26
|
+
def initialize(new_url = "http://www.gdacs.org/xml/rss.xml")
|
27
27
|
@url = new_url
|
28
28
|
@root_node = nil
|
29
29
|
begin
|
@@ -5,7 +5,7 @@ module SemanticCrawler
|
|
5
5
|
# One crisis entity with related resources. Could be one of the
|
6
6
|
# following crisis types:
|
7
7
|
#
|
8
|
-
# * Floods
|
8
|
+
# * Floods
|
9
9
|
# * Earthquakes
|
10
10
|
# * Tropical Cyclones
|
11
11
|
# * Volcanoes
|
@@ -124,16 +124,41 @@ module SemanticCrawler
|
|
124
124
|
query_root_node("gdacs:severity/text()", @@NAMESPACES)
|
125
125
|
end
|
126
126
|
|
127
|
+
# Returns the severity value (without further text)
|
128
|
+
def severity_value
|
129
|
+
query_root_node("gdacs:severity/@value", @@NAMESPACES)
|
130
|
+
end
|
131
|
+
|
132
|
+
# Returns the severity unit (without further text)
|
133
|
+
def severity_unit
|
134
|
+
query_root_node("gdacs:severity/@unit", @@NAMESPACES)
|
135
|
+
end
|
136
|
+
|
127
137
|
# Returns the population as human readable string
|
128
138
|
def population
|
129
139
|
query_root_node("gdacs:population/text()", @@NAMESPACES)
|
130
140
|
end
|
131
141
|
|
142
|
+
# Returns the population value (without further text)
|
143
|
+
def population_value
|
144
|
+
query_root_node("gdacs:population/@value", @@NAMESPACES)
|
145
|
+
end
|
146
|
+
|
147
|
+
# Returns the population unit (without further text)
|
148
|
+
def population_unit
|
149
|
+
query_root_node("gdacs:population/@unit", @@NAMESPACES)
|
150
|
+
end
|
151
|
+
|
132
152
|
# Returns the vulnerability as human readable string
|
133
153
|
def vulnerability
|
134
154
|
query_root_node("gdacs:vulnerability/text()", @@NAMESPACES)
|
135
155
|
end
|
136
156
|
|
157
|
+
# Returns the vulnerability as number
|
158
|
+
def vulnerability_value
|
159
|
+
query_root_node("gdacs:vulnerability/@value", @@NAMESPACES)
|
160
|
+
end
|
161
|
+
|
137
162
|
# Returns the country iso3 code if available
|
138
163
|
def iso3
|
139
164
|
query_root_node("gdacs:iso3/text()", @@NAMESPACES)
|
@@ -0,0 +1,55 @@
|
|
1
|
+
# encoding: UTF-8
|
2
|
+
|
3
|
+
module SemanticCrawler
|
4
|
+
module Gdacs
|
5
|
+
# The GDACS.org KML file contains geo information about the latest
|
6
|
+
# crises.
|
7
|
+
class KmlFile
|
8
|
+
|
9
|
+
# XML namespaces used for the parsing process
|
10
|
+
@@NAMESPACES = {
|
11
|
+
"k" => "http://www.opengis.net/kml/2.2"
|
12
|
+
}
|
13
|
+
|
14
|
+
# The gdacs.org KML file URL. (default:
|
15
|
+
# http://www.gdacs.org/xml/gdacs.kml)
|
16
|
+
attr_reader :url
|
17
|
+
|
18
|
+
# Initializes the gdacs.org KML file URL. If not specified the default
|
19
|
+
# URL (http://www..gdacs.org/xml/gdacs.kml) is used. Normally the
|
20
|
+
# file URL should not be changed.
|
21
|
+
def initialize(new_url = "http://www.gdacs.org/xml/gdacs.kml")
|
22
|
+
@url = new_url
|
23
|
+
@root_node = nil
|
24
|
+
begin
|
25
|
+
fetch_file
|
26
|
+
rescue => e
|
27
|
+
$log.error("Not able to get country information, through exception: #{e}")
|
28
|
+
end
|
29
|
+
end
|
30
|
+
|
31
|
+
def name
|
32
|
+
query_root_node("k:name/text()", @@NAMESPACES)
|
33
|
+
end
|
34
|
+
|
35
|
+
def placemark(crisis_id)
|
36
|
+
query_root_node("//k:Placemark[@id='#{crisis_id}']", @@NAMESPACES)
|
37
|
+
end
|
38
|
+
|
39
|
+
# Query the root node
|
40
|
+
def query_root_node(xpath_query, namespace = {})
|
41
|
+
if !@root_node.nil?
|
42
|
+
@root_node.xpath(xpath_query, namespace)
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
private
|
47
|
+
# Retrieves the RSS feed
|
48
|
+
def fetch_file
|
49
|
+
@doc = Nokogiri::XML(open(@url))
|
50
|
+
@root_node = @doc.xpath("/k:kml/k:Document", @@NAMESPACES)
|
51
|
+
end
|
52
|
+
|
53
|
+
end
|
54
|
+
end
|
55
|
+
end
|
data/semantic_crawler.gemspec
CHANGED
@@ -27,7 +27,7 @@ Gem::Specification.new do |s|
|
|
27
27
|
|
28
28
|
s.add_development_dependency "yard"
|
29
29
|
s.add_development_dependency "grit"
|
30
|
-
s.add_development_dependency "rails", "~> 3.2
|
30
|
+
s.add_development_dependency "rails", "~> 3.2"
|
31
31
|
s.add_development_dependency "sqlite3"
|
32
32
|
s.add_development_dependency "rspec-rails"
|
33
33
|
s.add_development_dependency "simplecov"
|
data/spec/gdacs_spec.rb
CHANGED
@@ -67,8 +67,13 @@ describe SemanticCrawler::Gdacs do
|
|
67
67
|
be_valid !item.eventid.nil?
|
68
68
|
be_valid !item.episodeid.nil?
|
69
69
|
be_valid !item.severity.nil?
|
70
|
+
be_valid !item.severity_value.nil?
|
71
|
+
be_valid !item.severity_unit.nil?
|
70
72
|
be_valid !item.population.nil?
|
73
|
+
be_valid !item.population_value.nil?
|
74
|
+
be_valid !item.population_value.nil?
|
71
75
|
be_valid !item.vulnerability.nil?
|
76
|
+
be_valid !item.vulnerability_value.nil?
|
72
77
|
be_valid !item.country.nil?
|
73
78
|
be_valid !item.iso3.nil?
|
74
79
|
be_valid !item.glide.nil?
|
@@ -89,6 +94,14 @@ describe SemanticCrawler::Gdacs do
|
|
89
94
|
end
|
90
95
|
end
|
91
96
|
|
97
|
+
xit "test kml file" do
|
98
|
+
kmlFile = SemanticCrawler::Gdacs::KmlFile.new
|
99
|
+
kmlFile.name.to_s.should_not be_empty
|
100
|
+
puts kmlFile.placemark("EQ_117653")
|
101
|
+
puts "----"
|
102
|
+
puts kmlFile.placemark("EQ_117653_Intensity")
|
103
|
+
end
|
104
|
+
|
92
105
|
it "test emergency feed" do
|
93
106
|
noFeed = SemanticCrawler::Gdacs::EmergencyFeed.new(nil)
|
94
107
|
be_valid noFeed.nil?
|
@@ -7,17 +7,17 @@ describe SemanticCrawler::LinkedGeoData do
|
|
7
7
|
#@dresden = SemanticCrawler::LinkedGeoData::RelevantNodes.new(51.033333, 13.733333, 1000, "TrafficSignals")
|
8
8
|
end
|
9
9
|
|
10
|
-
|
10
|
+
xit "check lat/long/radius of dresden" do
|
11
11
|
@dresden.latitude.to_s.should eq("51.033333")
|
12
12
|
@dresden.longitude.to_s.should eq("13.733333")
|
13
13
|
@dresden.radius.to_s.should eq("1000")
|
14
14
|
end
|
15
15
|
|
16
|
-
|
16
|
+
xit "output xml dump " do
|
17
17
|
@dresden.xml_document.size.should > 0
|
18
18
|
end
|
19
19
|
|
20
|
-
|
20
|
+
xit "check single relevant node entries" do
|
21
21
|
nodes = @dresden.relevant_nodes
|
22
22
|
nodes.each do |item|
|
23
23
|
item.xml_document.size.should > 0
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: semantic-crawler
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.6.0
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,7 +9,7 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2012-
|
12
|
+
date: 2012-08-04 00:00:00.000000000 Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: httparty
|
@@ -114,7 +114,7 @@ dependencies:
|
|
114
114
|
requirements:
|
115
115
|
- - ~>
|
116
116
|
- !ruby/object:Gem::Version
|
117
|
-
version: 3.2
|
117
|
+
version: '3.2'
|
118
118
|
type: :development
|
119
119
|
prerelease: false
|
120
120
|
version_requirements: !ruby/object:Gem::Requirement
|
@@ -122,7 +122,7 @@ dependencies:
|
|
122
122
|
requirements:
|
123
123
|
- - ~>
|
124
124
|
- !ruby/object:Gem::Version
|
125
|
-
version: 3.2
|
125
|
+
version: '3.2'
|
126
126
|
- !ruby/object:Gem::Dependency
|
127
127
|
name: sqlite3
|
128
128
|
requirement: !ruby/object:Gem::Requirement
|
@@ -206,7 +206,6 @@ files:
|
|
206
206
|
- MIT-LICENSE
|
207
207
|
- README.rdoc
|
208
208
|
- Rakefile
|
209
|
-
- exploitation/freebase.rb
|
210
209
|
- lib/semantic_crawler.rb
|
211
210
|
- lib/semantic_crawler/dbpedia.rb
|
212
211
|
- lib/semantic_crawler/factbook.rb
|
@@ -220,6 +219,7 @@ files:
|
|
220
219
|
- lib/semantic_crawler/gdacs/emergency_feed_item.rb
|
221
220
|
- lib/semantic_crawler/gdacs/feed.rb
|
222
221
|
- lib/semantic_crawler/gdacs/feed_item.rb
|
222
|
+
- lib/semantic_crawler/gdacs/kml_file.rb
|
223
223
|
- lib/semantic_crawler/gdacs/resource.rb
|
224
224
|
- lib/semantic_crawler/geo_names.rb
|
225
225
|
- lib/semantic_crawler/geo_names/country.rb
|
@@ -276,6 +276,7 @@ files:
|
|
276
276
|
- test/semantic_crawler_test.rb
|
277
277
|
- test/test_helper.rb
|
278
278
|
- test/dummy/log/test.log
|
279
|
+
- test/dummy/log/development.log
|
279
280
|
homepage: https://github.com/obale/semantic_crawler
|
280
281
|
licenses:
|
281
282
|
- MIT
|
@@ -291,7 +292,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
291
292
|
version: '0'
|
292
293
|
segments:
|
293
294
|
- 0
|
294
|
-
hash:
|
295
|
+
hash: 1493129874267030689
|
295
296
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
296
297
|
none: false
|
297
298
|
requirements:
|
@@ -300,55 +301,56 @@ required_rubygems_version: !ruby/object:Gem::Requirement
|
|
300
301
|
version: '0'
|
301
302
|
segments:
|
302
303
|
- 0
|
303
|
-
hash:
|
304
|
+
hash: 1493129874267030689
|
304
305
|
requirements: []
|
305
306
|
rubyforge_project:
|
306
|
-
rubygems_version: 1.8.
|
307
|
+
rubygems_version: 1.8.24
|
307
308
|
signing_key:
|
308
309
|
specification_version: 3
|
309
310
|
summary: SemanticCrawler is a ruby library that encapsulates data gathering from different
|
310
311
|
sources.
|
311
312
|
test_files:
|
313
|
+
- test/test_helper.rb
|
312
314
|
- test/semantic_crawler_test.rb
|
313
|
-
- test/dummy/
|
314
|
-
- test/dummy/
|
315
|
-
- test/dummy/
|
316
|
-
- test/dummy/
|
317
|
-
- test/dummy/
|
318
|
-
- test/dummy/
|
319
|
-
- test/dummy/config
|
320
|
-
- test/dummy/config/application.rb
|
315
|
+
- test/dummy/log/test.log
|
316
|
+
- test/dummy/log/development.log
|
317
|
+
- test/dummy/public/422.html
|
318
|
+
- test/dummy/public/favicon.ico
|
319
|
+
- test/dummy/public/500.html
|
320
|
+
- test/dummy/public/404.html
|
321
|
+
- test/dummy/config.ru
|
321
322
|
- test/dummy/config/locales/en.yml
|
322
|
-
- test/dummy/config/environments/test.rb
|
323
323
|
- test/dummy/config/environments/production.rb
|
324
|
+
- test/dummy/config/environments/test.rb
|
324
325
|
- test/dummy/config/environments/development.rb
|
325
|
-
- test/dummy/config/environment.rb
|
326
|
-
- test/dummy/config/database.yml
|
327
326
|
- test/dummy/config/boot.rb
|
328
|
-
- test/dummy/
|
327
|
+
- test/dummy/config/application.rb
|
328
|
+
- test/dummy/config/database.yml
|
329
|
+
- test/dummy/config/environment.rb
|
330
|
+
- test/dummy/config/routes.rb
|
331
|
+
- test/dummy/config/initializers/secret_token.rb
|
332
|
+
- test/dummy/config/initializers/inflections.rb
|
333
|
+
- test/dummy/config/initializers/backtrace_silencers.rb
|
334
|
+
- test/dummy/config/initializers/wrap_parameters.rb
|
335
|
+
- test/dummy/config/initializers/mime_types.rb
|
336
|
+
- test/dummy/config/initializers/session_store.rb
|
329
337
|
- test/dummy/script/rails
|
338
|
+
- test/dummy/README.rdoc
|
330
339
|
- test/dummy/db/development.sqlite3
|
331
340
|
- test/dummy/db/test.sqlite3
|
332
|
-
- test/dummy/public/500.html
|
333
|
-
- test/dummy/public/404.html
|
334
|
-
- test/dummy/public/favicon.ico
|
335
|
-
- test/dummy/public/422.html
|
336
|
-
- test/dummy/config.ru
|
337
341
|
- test/dummy/Rakefile
|
338
|
-
- test/dummy/app/
|
342
|
+
- test/dummy/app/helpers/application_helper.rb
|
339
343
|
- test/dummy/app/assets/stylesheets/application.css
|
340
|
-
- test/dummy/app/
|
344
|
+
- test/dummy/app/assets/javascripts/application.js
|
341
345
|
- test/dummy/app/controllers/application_controller.rb
|
342
|
-
- test/dummy/app/
|
343
|
-
-
|
344
|
-
- test/test_helper.rb
|
345
|
-
- spec/spec_helper.rb
|
346
|
-
- spec/fao_papua_new_guinea_spec.rb
|
347
|
-
- spec/freebase_spec.rb
|
346
|
+
- test/dummy/app/views/layouts/application.html.erb
|
347
|
+
- spec/linked_geo_data_spec.rb
|
348
348
|
- spec/factbook_spec.rb
|
349
|
+
- spec/fao_papua_new_guinea_spec.rb
|
349
350
|
- spec/dbpedia_spec.rb
|
350
|
-
- spec/fao_austria_spec.rb
|
351
351
|
- spec/geo_names_spec.rb
|
352
|
+
- spec/spec_helper.rb
|
353
|
+
- spec/freebase_spec.rb
|
352
354
|
- spec/gdacs_spec.rb
|
353
|
-
- spec/
|
355
|
+
- spec/fao_austria_spec.rb
|
354
356
|
has_rdoc:
|
data/exploitation/freebase.rb
DELETED
@@ -1,13 +0,0 @@
|
|
1
|
-
require 'cgi'
|
2
|
-
require 'httparty'
|
3
|
-
require 'json'
|
4
|
-
require 'pp'
|
5
|
-
|
6
|
-
#query = [{'id' => '/en/austria', 'name' => nil, 'type' => '/location/country', '*' => [{}] }]
|
7
|
-
query = [{'id' => '/en/austria', 'type' => '/type/property' }]
|
8
|
-
query_envelope = {'query' => query }
|
9
|
-
service_url = 'http://api.freebase.com/api/service/mqlread'
|
10
|
-
url = service_url + '?query=' + CGI::escape(query_envelope.to_json)
|
11
|
-
|
12
|
-
response = HTTParty.get(url, :format => :json)
|
13
|
-
puts response
|