nokogireader 0.1.0
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.
- checksums.yaml +7 -0
- data/.editorconfig +7 -0
- data/.gitignore +11 -0
- data/.rspec +2 -0
- data/Gemfile +3 -0
- data/LICENSE.txt +21 -0
- data/README.md +64 -0
- data/Rakefile +6 -0
- data/lib/nokogireader/definition.rb +46 -0
- data/lib/nokogireader/dsl.rb +36 -0
- data/lib/nokogireader/read_data.rb +44 -0
- data/lib/nokogireader/reader.rb +55 -0
- data/lib/nokogireader/version.rb +3 -0
- data/lib/nokogireader.rb +6 -0
- data/nokogireader.gemspec +28 -0
- metadata +142 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 87f220fc018df6ddaf21b6d471b707100e9d2af2
|
4
|
+
data.tar.gz: eea92fe211818fdc60cd3277cd49b65573e0fed8
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: dc4298a3e18265e17a772250e256121a3f0533a3cb5468a0981f2d3339ac38814b1d928231e8257cc9ae6a2d8a62ca117fa8f27b7fb3ebb5eacfff71e61fc6bc
|
7
|
+
data.tar.gz: 058206458c75294cdb5ece611255672e465030ae6e98e1df3e86983952b6bbd1bb04bae7cb4ccfb4c50936e112c4c9819a7878ef39e5cefdaf6390fddd982bdb
|
data/.editorconfig
ADDED
data/.gitignore
ADDED
data/.rspec
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2016 bonono
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,64 @@
|
|
1
|
+
# Nokogireader
|
2
|
+
|
3
|
+
DSL for parsing xml using Nokogiri::XML::Reader
|
4
|
+
|
5
|
+
## Installation
|
6
|
+
|
7
|
+
Add this line to your application's Gemfile:
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
gem 'nokogireader'
|
11
|
+
```
|
12
|
+
|
13
|
+
## Example
|
14
|
+
|
15
|
+
```rb
|
16
|
+
class Rss2 < Nokogireader::Reader
|
17
|
+
element :rss, attr: [:version] do
|
18
|
+
element :channel do
|
19
|
+
elements :item do
|
20
|
+
element :title
|
21
|
+
element :link
|
22
|
+
end
|
23
|
+
end
|
24
|
+
end
|
25
|
+
end
|
26
|
+
|
27
|
+
data = Rss2.new.read(File.open('rss2.xml'))
|
28
|
+
puts "Version: #{data[:rss].attributes[:version]}"
|
29
|
+
puts "Items: #{data[:rss][:channel][:item].size}"
|
30
|
+
data[:rss][:channel][:item].each do |item|
|
31
|
+
puts " > #{item[:title].text}"
|
32
|
+
end
|
33
|
+
```
|
34
|
+
|
35
|
+
You can use ``after`` callback and ``dont_store_data`` to reduce memory usage.
|
36
|
+
|
37
|
+
```rb
|
38
|
+
class Rss2 < Nokogireader::Reader
|
39
|
+
element :rss, attr: [:version] do
|
40
|
+
element :channel do
|
41
|
+
elements :item do
|
42
|
+
dont_store_data
|
43
|
+
element :title
|
44
|
+
element :link
|
45
|
+
|
46
|
+
after do |reader, item|
|
47
|
+
puts "Title: #{item[:title].text}"
|
48
|
+
end
|
49
|
+
end
|
50
|
+
end
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
data = data = Rss2.new.read(File.open('rss2.xml'))
|
55
|
+
puts "Items: #{data[:rss][:channel][:item].size}" # => 0. If specified "dont_store_data", data isn't stored.
|
56
|
+
```
|
57
|
+
|
58
|
+
## Contributing
|
59
|
+
|
60
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/bonono/nokogireader.
|
61
|
+
|
62
|
+
## License
|
63
|
+
|
64
|
+
The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
|
data/Rakefile
ADDED
@@ -0,0 +1,46 @@
|
|
1
|
+
module Nokogireader
|
2
|
+
class Definition
|
3
|
+
attr_reader :children
|
4
|
+
attr_accessor :read_attributes, :after_callback,
|
5
|
+
:accept_text, :multiple,
|
6
|
+
:dont_store_data
|
7
|
+
|
8
|
+
def initialize
|
9
|
+
@read_attributes = []
|
10
|
+
@after_callback = nil
|
11
|
+
@children = {}
|
12
|
+
@accept_text = false
|
13
|
+
@multiple = false
|
14
|
+
@dont_store_data = false
|
15
|
+
end
|
16
|
+
|
17
|
+
def configure(&block)
|
18
|
+
return self unless block_given?
|
19
|
+
DSL.new(self).instance_eval(&block)
|
20
|
+
self
|
21
|
+
end
|
22
|
+
|
23
|
+
def accept?(node)
|
24
|
+
if node.node_type == 1
|
25
|
+
@children.key?(node.name)
|
26
|
+
elsif node.node_type == 3
|
27
|
+
@accept_text
|
28
|
+
else
|
29
|
+
false
|
30
|
+
end
|
31
|
+
end
|
32
|
+
|
33
|
+
def multiple?
|
34
|
+
@multiple
|
35
|
+
end
|
36
|
+
|
37
|
+
def on_traversed(reader, data)
|
38
|
+
return unless @after_callback
|
39
|
+
if @after_callback.is_a?(Symbol)
|
40
|
+
reader.send(@after_callback, data)
|
41
|
+
else
|
42
|
+
@after_callback.call(reader, data)
|
43
|
+
end
|
44
|
+
end
|
45
|
+
end
|
46
|
+
end
|
@@ -0,0 +1,36 @@
|
|
1
|
+
module Nokogireader
|
2
|
+
# DSL to configure Nokogireader::Definition
|
3
|
+
class DSL
|
4
|
+
def initialize(definition)
|
5
|
+
@definition = definition
|
6
|
+
end
|
7
|
+
|
8
|
+
def element(name, opts = {}, &block)
|
9
|
+
@definition.children[name.to_s] =
|
10
|
+
create_child(opts, !block_given?).configure(&block)
|
11
|
+
end
|
12
|
+
|
13
|
+
def elements(name, opts = {}, &block)
|
14
|
+
child = create_child(opts, !block_given?)
|
15
|
+
child.multiple = true
|
16
|
+
@definition.children[name.to_s] = child.configure(&block)
|
17
|
+
end
|
18
|
+
|
19
|
+
def after(method_name = nil, &block)
|
20
|
+
@definition.after_callback = method_name || block
|
21
|
+
end
|
22
|
+
|
23
|
+
def dont_store_data
|
24
|
+
@definition.dont_store_data = true
|
25
|
+
end
|
26
|
+
|
27
|
+
private
|
28
|
+
|
29
|
+
def create_child(opts, accept_text)
|
30
|
+
child = Definition.new
|
31
|
+
child.accept_text = accept_text
|
32
|
+
child.read_attributes = opts[:attr] if opts[:attr]
|
33
|
+
child
|
34
|
+
end
|
35
|
+
end
|
36
|
+
end
|
@@ -0,0 +1,44 @@
|
|
1
|
+
module Nokogireader
|
2
|
+
class ReadData
|
3
|
+
attr_accessor :text
|
4
|
+
attr_reader :parent
|
5
|
+
|
6
|
+
def initialize(parent_data, definition, node)
|
7
|
+
@parent = parent_data
|
8
|
+
@definition = definition
|
9
|
+
@definition.read_attributes.each do |a|
|
10
|
+
attributes[a] = node.attribute(a.to_s)
|
11
|
+
end
|
12
|
+
end
|
13
|
+
|
14
|
+
def attributes
|
15
|
+
@attributes ||= {}
|
16
|
+
end
|
17
|
+
|
18
|
+
def children
|
19
|
+
@children ||= {}
|
20
|
+
end
|
21
|
+
|
22
|
+
def add_child(definition, node)
|
23
|
+
child = self.class.new(self, definition, node)
|
24
|
+
if definition.multiple?
|
25
|
+
(children[node.name] ||= []) << child
|
26
|
+
else
|
27
|
+
children[node.name] = child
|
28
|
+
end
|
29
|
+
child
|
30
|
+
end
|
31
|
+
|
32
|
+
def clear_child_for(node)
|
33
|
+
if children[node.name].is_a?(Array)
|
34
|
+
children[node.name].pop
|
35
|
+
else
|
36
|
+
children.delete(node.name)
|
37
|
+
end
|
38
|
+
end
|
39
|
+
|
40
|
+
def [](child_name)
|
41
|
+
children[child_name.to_s]
|
42
|
+
end
|
43
|
+
end
|
44
|
+
end
|
@@ -0,0 +1,55 @@
|
|
1
|
+
module Nokogireader
|
2
|
+
class Reader
|
3
|
+
def self.root_definition
|
4
|
+
@root ||= Definition.new
|
5
|
+
end
|
6
|
+
|
7
|
+
def self.element(name, opts = {}, &block)
|
8
|
+
root_definition.configure do
|
9
|
+
element(name, opts, &block)
|
10
|
+
end
|
11
|
+
end
|
12
|
+
|
13
|
+
def self.elements(name, opts = {}, &block)
|
14
|
+
root_definition.configure do
|
15
|
+
elements(name, opts, &block)
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
def read(xml)
|
20
|
+
root = self.class.root_definition
|
21
|
+
defstack = []
|
22
|
+
data = ReadData.new(nil, root, nil)
|
23
|
+
|
24
|
+
build_xml_reader(xml).each do |n|
|
25
|
+
if n.node_type == 1
|
26
|
+
d = defstack.last || root
|
27
|
+
defstack << (d.accept?(n) ? d.children[n.name] : nil)
|
28
|
+
data = data.add_child(defstack.last, n) if defstack.last
|
29
|
+
elsif n.node_type == 3
|
30
|
+
data.text = n.value if defstack.last && defstack.last.accept?(n)
|
31
|
+
end
|
32
|
+
|
33
|
+
if (n.node_type == 15 || n.self_closing?) && (old_def = defstack.pop)
|
34
|
+
old_def.on_traversed(self, data)
|
35
|
+
data = data.parent
|
36
|
+
data.clear_child_for(n) if old_def.dont_store_data
|
37
|
+
end
|
38
|
+
end
|
39
|
+
|
40
|
+
data
|
41
|
+
end
|
42
|
+
|
43
|
+
private
|
44
|
+
|
45
|
+
def build_xml_reader(source)
|
46
|
+
method_name = if source.kind_of?(IO) || source.kind_of?(StringIO)
|
47
|
+
:from_io
|
48
|
+
else
|
49
|
+
:from_memory
|
50
|
+
end
|
51
|
+
|
52
|
+
::Nokogiri::XML::Reader.send(method_name, source)
|
53
|
+
end
|
54
|
+
end
|
55
|
+
end
|
data/lib/nokogireader.rb
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'nokogireader/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "nokogireader"
|
8
|
+
spec.version = Nokogireader::VERSION
|
9
|
+
spec.authors = ["bonono"]
|
10
|
+
spec.email = ["bonono.jp@gmail.com"]
|
11
|
+
|
12
|
+
spec.summary = %q{DSL for parsing xml using Nokogiri::XML::Reader}
|
13
|
+
spec.homepage = "https://github.com/bonono/nokogireader"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
17
|
+
spec.bindir = "exe"
|
18
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_dependency 'nokogiri', '~> 1.6'
|
22
|
+
|
23
|
+
spec.add_development_dependency "bundler", "~> 1.11"
|
24
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
25
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
26
|
+
spec.add_development_dependency "rspec-its", "~> 1.0"
|
27
|
+
spec.add_development_dependency "simplecov"
|
28
|
+
end
|
metadata
ADDED
@@ -0,0 +1,142 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: nokogireader
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- bonono
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2016-08-12 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: nokogiri
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '1.6'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '1.6'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: bundler
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '1.11'
|
34
|
+
type: :development
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '1.11'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: rake
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '10.0'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '10.0'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rspec
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '3.0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '3.0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: rspec-its
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '1.0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '1.0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: simplecov
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - ">="
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - ">="
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0'
|
97
|
+
description:
|
98
|
+
email:
|
99
|
+
- bonono.jp@gmail.com
|
100
|
+
executables: []
|
101
|
+
extensions: []
|
102
|
+
extra_rdoc_files: []
|
103
|
+
files:
|
104
|
+
- ".editorconfig"
|
105
|
+
- ".gitignore"
|
106
|
+
- ".rspec"
|
107
|
+
- Gemfile
|
108
|
+
- LICENSE.txt
|
109
|
+
- README.md
|
110
|
+
- Rakefile
|
111
|
+
- lib/nokogireader.rb
|
112
|
+
- lib/nokogireader/definition.rb
|
113
|
+
- lib/nokogireader/dsl.rb
|
114
|
+
- lib/nokogireader/read_data.rb
|
115
|
+
- lib/nokogireader/reader.rb
|
116
|
+
- lib/nokogireader/version.rb
|
117
|
+
- nokogireader.gemspec
|
118
|
+
homepage: https://github.com/bonono/nokogireader
|
119
|
+
licenses:
|
120
|
+
- MIT
|
121
|
+
metadata: {}
|
122
|
+
post_install_message:
|
123
|
+
rdoc_options: []
|
124
|
+
require_paths:
|
125
|
+
- lib
|
126
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
127
|
+
requirements:
|
128
|
+
- - ">="
|
129
|
+
- !ruby/object:Gem::Version
|
130
|
+
version: '0'
|
131
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
132
|
+
requirements:
|
133
|
+
- - ">="
|
134
|
+
- !ruby/object:Gem::Version
|
135
|
+
version: '0'
|
136
|
+
requirements: []
|
137
|
+
rubyforge_project:
|
138
|
+
rubygems_version: 2.4.5.1
|
139
|
+
signing_key:
|
140
|
+
specification_version: 4
|
141
|
+
summary: DSL for parsing xml using Nokogiri::XML::Reader
|
142
|
+
test_files: []
|