hypermicrodata 0.1.0 → 0.1.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -7
- data/.travis.yml +3 -3
- data/lib/hypermicrodata/document.rb +5 -4
- data/lib/hypermicrodata/extract.rb +1 -1
- data/lib/hypermicrodata/version.rb +1 -1
- data/lib/hypermicrodata.rb +7 -5
- data/test/test_itemref.rb +6 -6
- data/test/test_json.rb +1 -1
- data/test/test_parse.rb +9 -9
- metadata +94 -65
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
|
-
---
|
2
|
-
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
5
|
-
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 31c2827d5ef761811004b563f135127def94a625
|
4
|
+
data.tar.gz: 229d52f8eee1e15347d72171d37f6ebda948df84
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: b1caaf52ab0fe4dc1c3285b04b9a1db8b3b1debe0d2966cc3c903d88a72e3900d3d2815521c95d5d98217e0c81cffe8f1d63fa9977e53d2ee1db361f8ea70de0
|
7
|
+
data.tar.gz: 3f2531028ea38dc3d082e84a14aa426406d7ebee8667e3459611ccfd05c7857eb965daf73715c5c390ef272989566b761386512955e940d4b6032bb821332dfb
|
data/.travis.yml
CHANGED
@@ -3,10 +3,11 @@ module Hypermicrodata
|
|
3
3
|
|
4
4
|
attr_reader :items, :doc
|
5
5
|
|
6
|
-
def initialize(content,
|
7
|
-
|
8
|
-
@
|
9
|
-
@
|
6
|
+
def initialize(content, options = {})
|
7
|
+
encoding = options[:force_encoding] || nil
|
8
|
+
@doc = Nokogiri::HTML(content, nil, encoding)
|
9
|
+
@page_url = options[:page_url]
|
10
|
+
@filter_xpath_attr = options[:filter_xpath_attr]
|
10
11
|
@items = extract_items
|
11
12
|
end
|
12
13
|
|
@@ -5,7 +5,7 @@ module Hypermicrodata
|
|
5
5
|
@location = options[:location]
|
6
6
|
@profile_path = options[:profile_path]
|
7
7
|
filter_xpath_attr = "@data-#{options[:data_attr_name] || default_data_attr_name}"
|
8
|
-
@document = Hypermicrodata::Document.new(html, @location, filter_xpath_attr)
|
8
|
+
@document = Hypermicrodata::Document.new(html, page_url: @location, filter_xpath_attr: filter_xpath_attr)
|
9
9
|
end
|
10
10
|
|
11
11
|
def to_json(format = :plain, options = {})
|
data/lib/hypermicrodata.rb
CHANGED
@@ -19,14 +19,16 @@ require 'uri'
|
|
19
19
|
|
20
20
|
module Hypermicrodata
|
21
21
|
|
22
|
-
def self.get_items(location)
|
23
|
-
|
22
|
+
def self.get_items(location, encoding = nil)
|
23
|
+
f = open(location)
|
24
24
|
page_url = location
|
25
|
-
Hypermicrodata::Document.new(
|
25
|
+
Hypermicrodata::Document.new(f, page_url: location, force_encoding: encoding).extract_items
|
26
|
+
ensure
|
27
|
+
f.close
|
26
28
|
end
|
27
29
|
|
28
|
-
def self.to_json(location)
|
29
|
-
items = get_items(location)
|
30
|
+
def self.to_json(location, encoding = nil)
|
31
|
+
items = get_items(location, encoding)
|
30
32
|
hash = {}
|
31
33
|
hash[:items] = items.map do |item|
|
32
34
|
item.to_hash
|
data/test/test_itemref.rb
CHANGED
@@ -3,17 +3,17 @@ require 'test_helper'
|
|
3
3
|
class TestItemref < Test::Unit::TestCase
|
4
4
|
|
5
5
|
def setup
|
6
|
-
@items = Hypermicrodata.get_items('test/data/example_itemref.html')
|
6
|
+
@items = Hypermicrodata.get_items('test/data/example_itemref.html', 'utf-8')
|
7
7
|
end
|
8
8
|
|
9
9
|
def test_top_item_name
|
10
|
-
assert_equal ['Amanda'], @items.first.properties['name']
|
10
|
+
assert_equal ['Amanda'], @items.first.properties['name'].map(&:value)
|
11
11
|
end
|
12
12
|
|
13
13
|
def test_band_name_and_size
|
14
|
-
band = @items.first.properties['band'].first
|
15
|
-
assert_equal ['Jazz Band'], band.properties['name']
|
16
|
-
assert_equal ['12'], band.properties['size']
|
14
|
+
band = @items.first.properties['band'].first.item
|
15
|
+
assert_equal ['Jazz Band'], band.properties['name'].map(&:value)
|
16
|
+
assert_equal ['12'], band.properties['size'].map(&:value)
|
17
17
|
end
|
18
18
|
|
19
|
-
end
|
19
|
+
end
|
data/test/test_json.rb
CHANGED
@@ -3,7 +3,7 @@ require 'test_helper'
|
|
3
3
|
class TestJson < Test::Unit::TestCase
|
4
4
|
|
5
5
|
def setup
|
6
|
-
json = Hypermicrodata.to_json('test/data/example_itemref.html')
|
6
|
+
json = Hypermicrodata.to_json('test/data/example_itemref.html', 'utf-8')
|
7
7
|
@top_item = JSON.parse(json)['items'].first
|
8
8
|
end
|
9
9
|
|
data/test/test_parse.rb
CHANGED
@@ -3,7 +3,7 @@ require 'test_helper'
|
|
3
3
|
class TestParse < Test::Unit::TestCase
|
4
4
|
|
5
5
|
def setup
|
6
|
-
@items = Hypermicrodata.get_items('test/data/example.html')
|
6
|
+
@items = Hypermicrodata.get_items('test/data/example.html', 'utf-8')
|
7
7
|
end
|
8
8
|
|
9
9
|
def test_top_item_type
|
@@ -16,21 +16,21 @@ class TestParse < Test::Unit::TestCase
|
|
16
16
|
|
17
17
|
def test_top_item_properties
|
18
18
|
properties = @items.first.properties
|
19
|
-
assert_equal ["Jason Ronallo"], properties['name']
|
20
|
-
assert_equal ["http://twitter.com/ronallo"], properties['url']
|
21
|
-
assert_equal ["Associate Head of Digital Library Initiatives"], properties['jobTitle']
|
19
|
+
assert_equal ["Jason Ronallo"], properties['name'].map(&:value)
|
20
|
+
assert_equal ["http://twitter.com/ronallo"], properties['url'].map(&:value)
|
21
|
+
assert_equal ["Associate Head of Digital Library Initiatives"], properties['jobTitle'].map(&:value)
|
22
22
|
end
|
23
23
|
|
24
24
|
def test_nested_item
|
25
|
-
item = @items.first.properties['affiliation']
|
25
|
+
item = @items.first.properties['affiliation'].first.item
|
26
26
|
assert_equal ['http://schema.org/Library'], item.type
|
27
27
|
assert_equal "http://lib.ncsu.edu", item.id
|
28
28
|
end
|
29
29
|
|
30
30
|
def test_nested_item_properties
|
31
|
-
properties = @items.first.properties['affiliation']
|
32
|
-
assert_equal ['NCSU Libraries'], properties['name']
|
33
|
-
assert_equal ['http://www.lib.ncsu.edu'], properties['url']
|
31
|
+
properties = @items.first.properties['affiliation'].first.item.properties
|
32
|
+
assert_equal ['NCSU Libraries'], properties['name'].map(&:value)
|
33
|
+
assert_equal ['http://www.lib.ncsu.edu'], properties['url'].map(&:value)
|
34
34
|
end
|
35
35
|
|
36
|
-
end
|
36
|
+
end
|
metadata
CHANGED
@@ -1,81 +1,109 @@
|
|
1
|
-
--- !ruby/object:Gem::Specification
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
2
|
name: hypermicrodata
|
3
|
-
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.1
|
5
5
|
platform: ruby
|
6
|
-
authors:
|
6
|
+
authors:
|
7
7
|
- Jason Ronallo
|
8
8
|
- Toru KAWAMURA
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
- !ruby/object:Gem::Dependency
|
12
|
+
date: 2014-10-13 00:00:00.000000000 Z
|
13
|
+
dependencies:
|
14
|
+
- !ruby/object:Gem::Dependency
|
16
15
|
name: nokogiri
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
- !ruby/object:Gem::Version
|
23
|
-
version: "0"
|
16
|
+
requirement: !ruby/object:Gem::Requirement
|
17
|
+
requirements:
|
18
|
+
- - '>='
|
19
|
+
- !ruby/object:Gem::Version
|
20
|
+
version: '0'
|
24
21
|
type: :runtime
|
25
|
-
version_requirements: *id001
|
26
|
-
- !ruby/object:Gem::Dependency
|
27
|
-
name: mechanize
|
28
22
|
prerelease: false
|
29
|
-
|
30
|
-
requirements:
|
31
|
-
-
|
23
|
+
version_requirements: !ruby/object:Gem::Requirement
|
24
|
+
requirements:
|
25
|
+
- - '>='
|
26
|
+
- !ruby/object:Gem::Version
|
27
|
+
version: '0'
|
28
|
+
- !ruby/object:Gem::Dependency
|
29
|
+
name: mechanize
|
30
|
+
requirement: !ruby/object:Gem::Requirement
|
31
|
+
requirements:
|
32
|
+
- - '>='
|
33
|
+
- !ruby/object:Gem::Version
|
34
|
+
version: '0'
|
32
35
|
type: :runtime
|
33
|
-
version_requirements: *id003
|
34
|
-
- !ruby/object:Gem::Dependency
|
35
|
-
name: halibut
|
36
36
|
prerelease: false
|
37
|
-
|
38
|
-
requirements:
|
39
|
-
-
|
37
|
+
version_requirements: !ruby/object:Gem::Requirement
|
38
|
+
requirements:
|
39
|
+
- - '>='
|
40
|
+
- !ruby/object:Gem::Version
|
41
|
+
version: '0'
|
42
|
+
- !ruby/object:Gem::Dependency
|
43
|
+
name: halibut
|
44
|
+
requirement: !ruby/object:Gem::Requirement
|
45
|
+
requirements:
|
46
|
+
- - '>='
|
47
|
+
- !ruby/object:Gem::Version
|
48
|
+
version: '0'
|
40
49
|
type: :runtime
|
41
|
-
version_requirements: *id004
|
42
|
-
- !ruby/object:Gem::Dependency
|
43
|
-
name: multi_json
|
44
50
|
prerelease: false
|
45
|
-
|
46
|
-
requirements:
|
47
|
-
-
|
51
|
+
version_requirements: !ruby/object:Gem::Requirement
|
52
|
+
requirements:
|
53
|
+
- - '>='
|
54
|
+
- !ruby/object:Gem::Version
|
55
|
+
version: '0'
|
56
|
+
- !ruby/object:Gem::Dependency
|
57
|
+
name: multi_json
|
58
|
+
requirement: !ruby/object:Gem::Requirement
|
59
|
+
requirements:
|
60
|
+
- - '>='
|
61
|
+
- !ruby/object:Gem::Version
|
62
|
+
version: '0'
|
48
63
|
type: :runtime
|
49
|
-
version_requirements: *id005
|
50
|
-
- !ruby/object:Gem::Dependency
|
51
|
-
name: bundler
|
52
64
|
prerelease: false
|
53
|
-
|
54
|
-
requirements:
|
65
|
+
version_requirements: !ruby/object:Gem::Requirement
|
66
|
+
requirements:
|
67
|
+
- - '>='
|
68
|
+
- !ruby/object:Gem::Version
|
69
|
+
version: '0'
|
70
|
+
- !ruby/object:Gem::Dependency
|
71
|
+
name: bundler
|
72
|
+
requirement: !ruby/object:Gem::Requirement
|
73
|
+
requirements:
|
55
74
|
- - ~>
|
56
|
-
- !ruby/object:Gem::Version
|
57
|
-
version:
|
75
|
+
- !ruby/object:Gem::Version
|
76
|
+
version: '1.3'
|
58
77
|
type: :development
|
59
|
-
version_requirements: *id006
|
60
|
-
- !ruby/object:Gem::Dependency
|
61
|
-
name: rake
|
62
78
|
prerelease: false
|
63
|
-
|
64
|
-
requirements:
|
65
|
-
-
|
79
|
+
version_requirements: !ruby/object:Gem::Requirement
|
80
|
+
requirements:
|
81
|
+
- - ~>
|
82
|
+
- !ruby/object:Gem::Version
|
83
|
+
version: '1.3'
|
84
|
+
- !ruby/object:Gem::Dependency
|
85
|
+
name: rake
|
86
|
+
requirement: !ruby/object:Gem::Requirement
|
87
|
+
requirements:
|
88
|
+
- - '>='
|
89
|
+
- !ruby/object:Gem::Version
|
90
|
+
version: '0'
|
66
91
|
type: :development
|
67
|
-
|
92
|
+
prerelease: false
|
93
|
+
version_requirements: !ruby/object:Gem::Requirement
|
94
|
+
requirements:
|
95
|
+
- - '>='
|
96
|
+
- !ruby/object:Gem::Version
|
97
|
+
version: '0'
|
68
98
|
description: HTML5 Microdata extractor with Hypermedia
|
69
|
-
email:
|
99
|
+
email:
|
70
100
|
- jronallo@gmail.com
|
71
101
|
- tkawa@4bit.net
|
72
|
-
executables:
|
102
|
+
executables:
|
73
103
|
- hypermicrodata.rb
|
74
104
|
extensions: []
|
75
|
-
|
76
105
|
extra_rdoc_files: []
|
77
|
-
|
78
|
-
files:
|
106
|
+
files:
|
79
107
|
- .gitignore
|
80
108
|
- .travis.yml
|
81
109
|
- Gemfile
|
@@ -107,29 +135,30 @@ files:
|
|
107
135
|
- test/test_json.rb
|
108
136
|
- test/test_parse.rb
|
109
137
|
homepage: https://github.com/tkawa/hypermicrodata
|
110
|
-
licenses:
|
138
|
+
licenses:
|
111
139
|
- MIT
|
112
140
|
metadata: {}
|
113
|
-
|
114
141
|
post_install_message:
|
115
142
|
rdoc_options: []
|
116
|
-
|
117
|
-
require_paths:
|
143
|
+
require_paths:
|
118
144
|
- lib
|
119
|
-
required_ruby_version: !ruby/object:Gem::Requirement
|
120
|
-
requirements:
|
121
|
-
-
|
122
|
-
|
123
|
-
|
124
|
-
|
145
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
146
|
+
requirements:
|
147
|
+
- - '>='
|
148
|
+
- !ruby/object:Gem::Version
|
149
|
+
version: '0'
|
150
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
151
|
+
requirements:
|
152
|
+
- - '>='
|
153
|
+
- !ruby/object:Gem::Version
|
154
|
+
version: '0'
|
125
155
|
requirements: []
|
126
|
-
|
127
156
|
rubyforge_project:
|
128
|
-
rubygems_version: 2.
|
157
|
+
rubygems_version: 2.4.2
|
129
158
|
signing_key:
|
130
159
|
specification_version: 4
|
131
160
|
summary: Ruby library for extracting HTML5 Microdata with Hypermedia
|
132
|
-
test_files:
|
161
|
+
test_files:
|
133
162
|
- test/data/example.html
|
134
163
|
- test/data/example_itemref.html
|
135
164
|
- test/data/example_with_no_itemscope.html
|