microformats2 2.0.0.pre4 → 2.0.0.pre5
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/README.md +2 -2
- data/lib/microformats2.rb +4 -7
- data/lib/microformats2/parser.rb +25 -0
- data/lib/microformats2/version.rb +1 -1
- data/microformats2.gemspec +1 -1
- data/spec/lib/microformats2/parser_spec.rb +41 -0
- data/spec/lib/microformats2_spec.rb +3 -0
- data/spec/spec_helper.rb +1 -0
- metadata +9 -8
data/README.md
CHANGED
|
@@ -10,7 +10,7 @@ A work in progress.
|
|
|
10
10
|
|
|
11
11
|
Implemented:
|
|
12
12
|
|
|
13
|
-
* [parsing depth first, doc order](parse_a_document_for_microformats)
|
|
13
|
+
* [parsing depth first, doc order](http://microformats.org/wiki/microformats2-parsing#parse_a_document_for_microformats)
|
|
14
14
|
* [parsing a p- property](http://microformats.org/wiki/microformats2-parsing#parsing_a_p-_property)
|
|
15
15
|
* [parsing a u- property](http://microformats.org/wiki/microformats2-parsing#parsing_a_u-_property)
|
|
16
16
|
* [parsing a dt- property](http://microformats.org/wiki/microformats2-parsing#parsing_a_dt-_property)
|
|
@@ -33,7 +33,7 @@ Not Implemented:
|
|
|
33
33
|
|
|
34
34
|
## Current Version
|
|
35
35
|
|
|
36
|
-
2.0.0.
|
|
36
|
+
2.0.0.pre5
|
|
37
37
|
|
|
38
38
|
|
|
39
39
|
## Requirements
|
data/lib/microformats2.rb
CHANGED
|
@@ -4,6 +4,7 @@ require "json"
|
|
|
4
4
|
require "active_support/inflector"
|
|
5
5
|
|
|
6
6
|
require "microformats2/version"
|
|
7
|
+
require "microformats2/parser"
|
|
7
8
|
require "microformats2/format_parser"
|
|
8
9
|
require "microformats2/property_parser"
|
|
9
10
|
require "microformats2/collection"
|
|
@@ -22,17 +23,13 @@ require "microformats2/implied_property/url"
|
|
|
22
23
|
module Microformats2
|
|
23
24
|
class << self
|
|
24
25
|
def parse(html)
|
|
25
|
-
|
|
26
|
-
document = Nokogiri::HTML(html)
|
|
27
|
-
Collection.new(document).parse
|
|
26
|
+
Parser.new.parse(html)
|
|
28
27
|
end
|
|
29
28
|
|
|
30
29
|
def read_html(html)
|
|
31
|
-
|
|
32
|
-
rescue Errno::ENOENT, Errno::ENAMETOOLONG => e
|
|
33
|
-
html
|
|
30
|
+
Parser.new.read_html(html)
|
|
34
31
|
end
|
|
35
32
|
end # class << self
|
|
36
33
|
|
|
37
34
|
class InvalidPropertyPrefix < StandardError; end
|
|
38
|
-
end
|
|
35
|
+
end
|
|
@@ -0,0 +1,25 @@
|
|
|
1
|
+
module Microformats2
|
|
2
|
+
class Parser
|
|
3
|
+
attr_reader :http_headers, :http_body
|
|
4
|
+
|
|
5
|
+
def initialize
|
|
6
|
+
@http_headers = {}
|
|
7
|
+
end
|
|
8
|
+
|
|
9
|
+
def parse(html, headers={})
|
|
10
|
+
html = read_html(html, headers)
|
|
11
|
+
document = Nokogiri::HTML(html)
|
|
12
|
+
Collection.new(document).parse
|
|
13
|
+
end
|
|
14
|
+
|
|
15
|
+
def read_html(html, headers={})
|
|
16
|
+
open(html, headers) do |response|
|
|
17
|
+
@http_headers = response.meta if response.respond_to?(:meta)
|
|
18
|
+
@http_body = response.read
|
|
19
|
+
end
|
|
20
|
+
@http_body
|
|
21
|
+
rescue Errno::ENOENT, Errno::ENAMETOOLONG => e
|
|
22
|
+
@http_body = html
|
|
23
|
+
end
|
|
24
|
+
end
|
|
25
|
+
end
|
data/microformats2.gemspec
CHANGED
|
@@ -26,5 +26,5 @@ Gem::Specification.new do |gem|
|
|
|
26
26
|
gem.add_development_dependency "guard-rspec", "~> 2.1.0"
|
|
27
27
|
gem.add_development_dependency "rb-fsevent", "~> 0.9.1"
|
|
28
28
|
gem.add_development_dependency "simplecov", "~> 0.7.1"
|
|
29
|
-
gem.add_development_dependency "
|
|
29
|
+
gem.add_development_dependency "webmock", "~> 1.12.3"
|
|
30
30
|
end
|
|
@@ -0,0 +1,41 @@
|
|
|
1
|
+
require "spec_helper"
|
|
2
|
+
require "microformats2"
|
|
3
|
+
|
|
4
|
+
describe Microformats2::Parser do
|
|
5
|
+
let(:parser) { Microformats2::Parser.new }
|
|
6
|
+
|
|
7
|
+
describe "#http_headers" do
|
|
8
|
+
it "starts as a blank hash" do
|
|
9
|
+
parser.http_headers.should eq({})
|
|
10
|
+
end
|
|
11
|
+
|
|
12
|
+
describe "open file" do
|
|
13
|
+
before do
|
|
14
|
+
parser.parse("spec/support/lib/microformats2/simple.html")
|
|
15
|
+
end
|
|
16
|
+
|
|
17
|
+
it "doesn't save #http_headers" do
|
|
18
|
+
parser.http_headers.should eq({})
|
|
19
|
+
end
|
|
20
|
+
it "saves #http_body" do
|
|
21
|
+
parser.http_body.should include "<!DOCTYPE html>"
|
|
22
|
+
end
|
|
23
|
+
end
|
|
24
|
+
|
|
25
|
+
describe "http response" do
|
|
26
|
+
before do
|
|
27
|
+
stub_request(:get, "http://www.example.com/").
|
|
28
|
+
with(:headers => {"Accept"=>"*/*", "User-Agent"=>"Ruby"}).
|
|
29
|
+
to_return(:status => 200, :body => "abc", :headers => {"Content-Length" => 3})
|
|
30
|
+
parser.parse("http://www.example.com")
|
|
31
|
+
end
|
|
32
|
+
|
|
33
|
+
it "saves #http_headers" do
|
|
34
|
+
parser.http_headers.should eq({"content-length" => "3"})
|
|
35
|
+
end
|
|
36
|
+
it "saves #http_body" do
|
|
37
|
+
parser.http_body.should eq("abc")
|
|
38
|
+
end
|
|
39
|
+
end
|
|
40
|
+
end
|
|
41
|
+
end
|
|
@@ -23,6 +23,9 @@ describe Microformats2 do
|
|
|
23
23
|
Microformats2.read_html(html).should include "<div class=\"h-card\">"
|
|
24
24
|
end
|
|
25
25
|
it "can be a url to html" do
|
|
26
|
+
stub_request(:get, "http://google.com/").
|
|
27
|
+
with(:headers => {'Accept'=>'*/*', 'User-Agent'=>'Ruby'}).
|
|
28
|
+
to_return(:status => 200, :body => "google", :headers => {})
|
|
26
29
|
html = "http://google.com"
|
|
27
30
|
Microformats2.read_html(html).should include "google"
|
|
28
31
|
end
|
data/spec/spec_helper.rb
CHANGED
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: microformats2
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 2.0.0.
|
|
4
|
+
version: 2.0.0.pre5
|
|
5
5
|
prerelease: 6
|
|
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: 2013-
|
|
12
|
+
date: 2013-07-02 00:00:00.000000000 Z
|
|
13
13
|
dependencies:
|
|
14
14
|
- !ruby/object:Gem::Dependency
|
|
15
15
|
name: nokogiri
|
|
@@ -140,13 +140,13 @@ dependencies:
|
|
|
140
140
|
- !ruby/object:Gem::Version
|
|
141
141
|
version: 0.7.1
|
|
142
142
|
- !ruby/object:Gem::Dependency
|
|
143
|
-
name:
|
|
143
|
+
name: webmock
|
|
144
144
|
requirement: !ruby/object:Gem::Requirement
|
|
145
145
|
none: false
|
|
146
146
|
requirements:
|
|
147
147
|
- - ~>
|
|
148
148
|
- !ruby/object:Gem::Version
|
|
149
|
-
version: 1.
|
|
149
|
+
version: 1.12.3
|
|
150
150
|
type: :development
|
|
151
151
|
prerelease: false
|
|
152
152
|
version_requirements: !ruby/object:Gem::Requirement
|
|
@@ -154,7 +154,7 @@ dependencies:
|
|
|
154
154
|
requirements:
|
|
155
155
|
- - ~>
|
|
156
156
|
- !ruby/object:Gem::Version
|
|
157
|
-
version: 1.
|
|
157
|
+
version: 1.12.3
|
|
158
158
|
description: parses HTML for microformats and return a collection of dynamically defined
|
|
159
159
|
Ruby objects
|
|
160
160
|
email:
|
|
@@ -179,6 +179,7 @@ files:
|
|
|
179
179
|
- lib/microformats2/implied_property/name.rb
|
|
180
180
|
- lib/microformats2/implied_property/photo.rb
|
|
181
181
|
- lib/microformats2/implied_property/url.rb
|
|
182
|
+
- lib/microformats2/parser.rb
|
|
182
183
|
- lib/microformats2/property.rb
|
|
183
184
|
- lib/microformats2/property/date_time.rb
|
|
184
185
|
- lib/microformats2/property/embedded.rb
|
|
@@ -192,6 +193,7 @@ files:
|
|
|
192
193
|
- spec/lib/microformats2/implied_property/name_spec.rb
|
|
193
194
|
- spec/lib/microformats2/implied_property/photo_spec.rb
|
|
194
195
|
- spec/lib/microformats2/implied_property/url_spec.rb
|
|
196
|
+
- spec/lib/microformats2/parser_spec.rb
|
|
195
197
|
- spec/lib/microformats2_spec.rb
|
|
196
198
|
- spec/spec_helper.rb
|
|
197
199
|
- spec/support/cases/microformat2-node.jit.su/h-adr/h-adr-0.html
|
|
@@ -371,9 +373,6 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
|
371
373
|
- - ! '>='
|
|
372
374
|
- !ruby/object:Gem::Version
|
|
373
375
|
version: '0'
|
|
374
|
-
segments:
|
|
375
|
-
- 0
|
|
376
|
-
hash: 2813270681629112276
|
|
377
376
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
378
377
|
none: false
|
|
379
378
|
requirements:
|
|
@@ -391,6 +390,7 @@ test_files:
|
|
|
391
390
|
- spec/lib/microformats2/implied_property/name_spec.rb
|
|
392
391
|
- spec/lib/microformats2/implied_property/photo_spec.rb
|
|
393
392
|
- spec/lib/microformats2/implied_property/url_spec.rb
|
|
393
|
+
- spec/lib/microformats2/parser_spec.rb
|
|
394
394
|
- spec/lib/microformats2_spec.rb
|
|
395
395
|
- spec/spec_helper.rb
|
|
396
396
|
- spec/support/cases/microformat2-node.jit.su/h-adr/h-adr-0.html
|
|
@@ -558,3 +558,4 @@ test_files:
|
|
|
558
558
|
- spec/support/lib/microformats2/nested-property.js
|
|
559
559
|
- spec/support/lib/microformats2/simple.html
|
|
560
560
|
- spec/support/lib/microformats2/simple.js
|
|
561
|
+
has_rdoc:
|