alexrabarts-term_extraction 0.1.1 → 0.1.2
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/VERSION.yml +1 -1
- data/lib/term_extraction/yahoo.rb +2 -5
- data/lib/term_extraction/zemanta.rb +2 -5
- data/test/fixtures/yahoo2.xml +3 -0
- data/test/fixtures/zemanta2.xml +104 -0
- data/test/term_extraction_test.rb +16 -0
- metadata +3 -1
data/VERSION.yml
CHANGED
|
@@ -3,7 +3,8 @@ require 'nokogiri'
|
|
|
3
3
|
class TermExtraction
|
|
4
4
|
class Yahoo < TermExtraction
|
|
5
5
|
def terms
|
|
6
|
-
terms
|
|
6
|
+
terms = []
|
|
7
|
+
data = Nokogiri::XML.parse(remote_xml)
|
|
7
8
|
|
|
8
9
|
unless data.nil?
|
|
9
10
|
data.search('//s:Result', ns).each do |n|
|
|
@@ -43,9 +44,5 @@ class TermExtraction
|
|
|
43
44
|
def remote_xml
|
|
44
45
|
open(url).read
|
|
45
46
|
end
|
|
46
|
-
|
|
47
|
-
def data
|
|
48
|
-
@data ||= Nokogiri::XML.parse(remote_xml)
|
|
49
|
-
end
|
|
50
47
|
end
|
|
51
48
|
end
|
|
@@ -5,13 +5,14 @@ class TermExtraction
|
|
|
5
5
|
class Zemanta < TermExtraction
|
|
6
6
|
def terms
|
|
7
7
|
terms = []
|
|
8
|
+
data = Nokogiri::XML.parse(remote_xml)
|
|
8
9
|
|
|
9
10
|
data.search('//name').each do |n|
|
|
10
11
|
terms << n.text
|
|
11
12
|
end
|
|
12
13
|
|
|
13
14
|
terms
|
|
14
|
-
end
|
|
15
|
+
end
|
|
15
16
|
|
|
16
17
|
class << self
|
|
17
18
|
def canonical_name
|
|
@@ -41,9 +42,5 @@ class TermExtraction
|
|
|
41
42
|
def remote_xml
|
|
42
43
|
Net::HTTP.post_form(url, post_params).body
|
|
43
44
|
end
|
|
44
|
-
|
|
45
|
-
def data
|
|
46
|
-
@data ||= Nokogiri::XML.parse(remote_xml)
|
|
47
|
-
end
|
|
48
45
|
end
|
|
49
46
|
end
|
|
@@ -0,0 +1,3 @@
|
|
|
1
|
+
<?xml version="1.0"?>
|
|
2
|
+
<ResultSet xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="urn:yahoo:cate" xsi:schemaLocation="urn:yahoo:cate http://api.search.yahoo.com/ContentAnalysisService/V1/TermExtractionResponse.xsd"><Result>fears of war</Result><Result>fears</Result></ResultSet>
|
|
3
|
+
<!-- ws04.search.scd.yahoo.com uncompressed/chunked Thu Feb 26 21:04:16 PST 2009 -->
|
|
@@ -0,0 +1,104 @@
|
|
|
1
|
+
<?xml version="1.0"?>
|
|
2
|
+
<rsp>
|
|
3
|
+
<status>ok</status>
|
|
4
|
+
<articles>
|
|
5
|
+
<article>
|
|
6
|
+
<url>http://www.crunchgear.com/2009/02/24/nvidia-based-imacs-coming-soon/</url>
|
|
7
|
+
<confidence>0.033153</confidence>
|
|
8
|
+
<published_datetime>2009-02-24T18:00:45Z</published_datetime>
|
|
9
|
+
<zemified>0</zemified>
|
|
10
|
+
<title>NVIDIA-based iMacs coming soon?</title>
|
|
11
|
+
</article><article>
|
|
12
|
+
<url>http://www.tuaw.com/2009/02/24/rumor-new-imacs-around-the-bend/</url>
|
|
13
|
+
<confidence>0.028595</confidence>
|
|
14
|
+
<published_datetime>2009-02-24T22:00:00Z</published_datetime>
|
|
15
|
+
<zemified>0</zemified>
|
|
16
|
+
<title>Rumor: New iMacs around the bend</title>
|
|
17
|
+
</article><article>
|
|
18
|
+
<url>http://www.engadget.com/2009/02/24/a-few-new-rumors-point-to-two-new-nvidia-packing-imacs/</url>
|
|
19
|
+
<confidence>0.027595</confidence>
|
|
20
|
+
<published_datetime>2009-02-24T13:03:00Z</published_datetime>
|
|
21
|
+
<zemified>0</zemified>
|
|
22
|
+
<title>A few new rumors point to two new NVIDIA-packing iMacs</title>
|
|
23
|
+
</article><article>
|
|
24
|
+
<url>http://www.techmeme.com/090126/p31</url>
|
|
25
|
+
<confidence>0.019056</confidence>
|
|
26
|
+
<published_datetime>2009-01-26T17:00:22Z</published_datetime>
|
|
27
|
+
<zemified>0</zemified>
|
|
28
|
+
<title>Chip complex delaying Apple's new iMac line, says analyst (Zach Spear/AppleInsider)</title>
|
|
29
|
+
</article><article>
|
|
30
|
+
<url>http://i.gizmodo.com/5143476/apple-warns-resellers-of-reduced-imac-availability-new-models-on-the-way</url>
|
|
31
|
+
<confidence>0.018611</confidence>
|
|
32
|
+
<published_datetime>2009-01-31T16:30:00Z</published_datetime>
|
|
33
|
+
<zemified>0</zemified>
|
|
34
|
+
<title>Apple Warns Resellers of Reduced iMac Availability: New Models On the Way? [Apple]</title>
|
|
35
|
+
</article><article>
|
|
36
|
+
<url>http://cultofmac.com/analyst-new-imacs-delayed-for-chips-snow-leopard/7549</url>
|
|
37
|
+
<confidence>0.01685</confidence>
|
|
38
|
+
<published_datetime>2009-01-26T16:43:44Z</published_datetime>
|
|
39
|
+
<zemified>0</zemified>
|
|
40
|
+
<title>Analyst: New iMacs Delayed For Chips, Snow Leopard</title>
|
|
41
|
+
</article><article>
|
|
42
|
+
<url>http://www.ubergizmo.com/15/archives/2008/12/new_imac_allinone_pc_confirmed.html</url>
|
|
43
|
+
<confidence>0.016311</confidence>
|
|
44
|
+
<published_datetime>2008-12-24T01:06:56Z</published_datetime>
|
|
45
|
+
<zemified>0</zemified>
|
|
46
|
+
<title>New iMac All-In-One PC Confirmed</title>
|
|
47
|
+
</article><article>
|
|
48
|
+
<url>http://www.labnol.org/gadgets/exchange-windows-pc-for-apple-mac/5775/</url>
|
|
49
|
+
<confidence>0.016238</confidence>
|
|
50
|
+
<published_datetime>2008-12-03T08:17:35Z</published_datetime>
|
|
51
|
+
<zemified>0</zemified>
|
|
52
|
+
<title>Exchange Your Windows PC or TV for an Apple iMac</title>
|
|
53
|
+
</article><article>
|
|
54
|
+
<url>http://cultofmac.com/class-action-lawsuit-over-imac-display-problems/6562</url>
|
|
55
|
+
<confidence>0.015608</confidence>
|
|
56
|
+
<published_datetime>2009-01-02T16:17:06Z</published_datetime>
|
|
57
|
+
<zemified>0</zemified>
|
|
58
|
+
<title>Class-Action Lawsuit Over iMac Display Problems</title>
|
|
59
|
+
</article><article>
|
|
60
|
+
<url>http://www.crunchgear.com/2008/12/29/new-imacs-to-include-hotter-components-new-cooling/</url>
|
|
61
|
+
<confidence>0.015093</confidence>
|
|
62
|
+
<published_datetime>2008-12-29T23:50:04Z</published_datetime>
|
|
63
|
+
<zemified>0</zemified>
|
|
64
|
+
<title>New iMacs to include hotter components, new cooling?</title>
|
|
65
|
+
</article>
|
|
66
|
+
</articles><markup>
|
|
67
|
+
<text>apple imac</text>
|
|
68
|
+
</markup><signature><div class="zemanta-pixie"><a class="zemanta-pixie-a" href="http://reblog.zemanta.com/zemified/3695b55a-d68e-4328-bf86-c3f01be8b2da/" title="Zemified by Zemanta"><img class="zemanta-pixie-img" src="http://img.zemanta.com/reblog_e.png?x-id=3695b55a-d68e-4328-bf86-c3f01be8b2da" alt="Reblog this post [with Zemanta]" /></a></div></signature>
|
|
69
|
+
<keywords>
|
|
70
|
+
<keyword>
|
|
71
|
+
<confidence>0.404748</confidence>
|
|
72
|
+
<scheme>general</scheme>
|
|
73
|
+
<name>Zapple</name>
|
|
74
|
+
</keyword><keyword>
|
|
75
|
+
<confidence>0.277753</confidence>
|
|
76
|
+
<scheme>general</scheme>
|
|
77
|
+
<name>AMac</name>
|
|
78
|
+
</keyword><keyword>
|
|
79
|
+
<confidence>0.094392</confidence>
|
|
80
|
+
<scheme>general</scheme>
|
|
81
|
+
<name>Tumor</name>
|
|
82
|
+
</keyword><keyword>
|
|
83
|
+
<confidence>0.076399</confidence>
|
|
84
|
+
<scheme>general</scheme>
|
|
85
|
+
<name>Shardware</name>
|
|
86
|
+
</keyword><keyword>
|
|
87
|
+
<confidence>0.072186</confidence>
|
|
88
|
+
<scheme>general</scheme>
|
|
89
|
+
<name>Mvidia</name>
|
|
90
|
+
</keyword><keyword>
|
|
91
|
+
<confidence>0.069183</confidence>
|
|
92
|
+
<scheme>general</scheme>
|
|
93
|
+
<name>Hackintosh</name>
|
|
94
|
+
</keyword><keyword>
|
|
95
|
+
<confidence>0.050487</confidence>
|
|
96
|
+
<scheme>general</scheme>
|
|
97
|
+
<name>Zesktops</name>
|
|
98
|
+
</keyword><keyword>
|
|
99
|
+
<confidence>0.039205</confidence>
|
|
100
|
+
<scheme>general</scheme>
|
|
101
|
+
<name>AllInNone</name>
|
|
102
|
+
</keyword>
|
|
103
|
+
</keywords><rid>3695b55a-d68e-4328-bf86-c3f01be8b2da</rid>
|
|
104
|
+
</rsp>
|
|
@@ -27,6 +27,22 @@ class TermExtractionTest < Test::Unit::TestCase
|
|
|
27
27
|
assert_equal zemanta.context, context
|
|
28
28
|
end
|
|
29
29
|
|
|
30
|
+
should 'return different response on subsequent calls when different data is returned from Yahoo!' do
|
|
31
|
+
yahoo = TermExtraction::Yahoo.new
|
|
32
|
+
yahoo.stubs(:remote_xml).returns(read_xml_fixture('yahoo'))
|
|
33
|
+
original_terms = yahoo.terms
|
|
34
|
+
yahoo.stubs(:remote_xml).returns(read_xml_fixture('yahoo2'))
|
|
35
|
+
assert_not_equal original_terms, yahoo.terms
|
|
36
|
+
end
|
|
37
|
+
|
|
38
|
+
should 'return different response on subsequent calls when different data is returned from Zemanta' do
|
|
39
|
+
zemanta = TermExtraction::Zemanta.new
|
|
40
|
+
zemanta.stubs(:remote_xml).returns(read_xml_fixture('zemanta'))
|
|
41
|
+
original_terms = zemanta.terms
|
|
42
|
+
zemanta.stubs(:remote_xml).returns(read_xml_fixture('zemanta2'))
|
|
43
|
+
assert_not_equal original_terms, zemanta.terms
|
|
44
|
+
end
|
|
45
|
+
|
|
30
46
|
private
|
|
31
47
|
def correct_yahoo_terms
|
|
32
48
|
['gears of war', 'gears']
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: alexrabarts-term_extraction
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.1.
|
|
4
|
+
version: 0.1.2
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- alex
|
|
@@ -38,7 +38,9 @@ files:
|
|
|
38
38
|
- lib/term_extraction.rb
|
|
39
39
|
- test/fixtures
|
|
40
40
|
- test/fixtures/yahoo.xml
|
|
41
|
+
- test/fixtures/yahoo2.xml
|
|
41
42
|
- test/fixtures/zemanta.xml
|
|
43
|
+
- test/fixtures/zemanta2.xml
|
|
42
44
|
- test/term_extraction_test.rb
|
|
43
45
|
- test/test_helper.rb
|
|
44
46
|
has_rdoc: true
|