sax-machine 0.2.1 → 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +2 -0
- data/.travis.yml +14 -4
- data/Gemfile +5 -1
- data/Guardfile +2 -2
- data/HISTORY.md +23 -6
- data/README.md +111 -40
- data/Rakefile +4 -3
- data/lib/sax-machine.rb +11 -2
- data/lib/sax-machine/{sax_ancestor_config.rb → config/sax_ancestor.rb} +3 -7
- data/lib/sax-machine/{sax_attribute_config.rb → config/sax_attribute.rb} +4 -6
- data/lib/sax-machine/{sax_collection_config.rb → config/sax_collection.rb} +6 -10
- data/lib/sax-machine/{sax_element_config.rb → config/sax_element.rb} +16 -17
- data/lib/sax-machine/{sax_element_value_config.rb → config/sax_element_value.rb} +5 -7
- data/lib/sax-machine/{sax_handler.rb → handlers/sax_abstract_handler.rb} +28 -32
- data/lib/sax-machine/handlers/sax_nokogiri_handler.rb +16 -0
- data/lib/sax-machine/handlers/sax_ox_handler.rb +41 -0
- data/lib/sax-machine/sax_config.rb +9 -9
- data/lib/sax-machine/sax_configure.rb +1 -6
- data/lib/sax-machine/sax_document.rb +28 -17
- data/lib/sax-machine/version.rb +2 -2
- data/sax-machine.gemspec +8 -11
- data/spec/fixtures/atom-content.html +15 -0
- data/spec/{sax-machine → fixtures}/atom.xml +0 -0
- data/spec/sax-machine/sax_activerecord_spec.rb +23 -0
- data/spec/sax-machine/sax_configure_spec.rb +48 -0
- data/spec/sax-machine/sax_document_spec.rb +333 -280
- data/spec/sax-machine/sax_include_spec.rb +43 -0
- data/spec/spec_helper.rb +11 -2
- metadata +36 -41
- data/spec/benchmarks/amazon.xml +0 -40
- data/spec/benchmarks/benchmark.rb +0 -158
- data/spec/benchmarks/public_timeline.xml +0 -411
- data/spec/sax-machine/configure_sax_machine_spec.rb +0 -53
- data/spec/sax-machine/include_sax_machine_spec.rb +0 -42
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: eced69c84dfa4d14f4e55e8f8f57af2c90f69281
|
4
|
+
data.tar.gz: a00ec939b3a116885109a44283c68d0d301ebb63
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: e728531fb1931246e61c4ecc5182f51f30ec2d7b4131976c282313f2db08c324a679c6f58f01fd02c2816fae380e4c711324764ca8cc192c04f4d8702218640f
|
7
|
+
data.tar.gz: 3014692c51809a0dd4cd0f0656fdc63d6d669ad9d3ba863fec64ac5aa0238a7b0dda83658b693ff4de800d8073ddf55d0bb6f32f7b3ac4370bbb24da9428606b
|
data/.gitignore
CHANGED
data/.travis.yml
CHANGED
@@ -1,12 +1,22 @@
|
|
1
1
|
language: ruby
|
2
2
|
rvm:
|
3
|
-
- 1.9.2
|
4
3
|
- 1.9.3
|
5
|
-
- 2.0
|
4
|
+
- 2.0
|
5
|
+
- 2.1
|
6
|
+
- jruby-1.7
|
7
|
+
- rbx-2
|
6
8
|
- ruby-head
|
7
|
-
- jruby-19mode
|
8
9
|
- jruby-head
|
9
|
-
- rbx-19mode
|
10
10
|
matrix:
|
11
11
|
allow_failures:
|
12
|
+
- rvm: rbx-2
|
12
13
|
- rvm: ruby-head
|
14
|
+
- rvm: jruby-head
|
15
|
+
- env: HANDLER="ox"
|
16
|
+
rvm: jruby-1.7
|
17
|
+
- env: HANDLER="ox"
|
18
|
+
rvm: jruby-head
|
19
|
+
env:
|
20
|
+
matrix:
|
21
|
+
- HANDLER="nokogiri"
|
22
|
+
- HANDLER="ox"
|
data/Gemfile
CHANGED
@@ -5,5 +5,9 @@ gemspec
|
|
5
5
|
group :development, :test do
|
6
6
|
gem 'rake'
|
7
7
|
gem 'guard-rspec'
|
8
|
-
gem 'simplecov', :
|
8
|
+
gem 'simplecov', require: false, platforms: [:mri]
|
9
|
+
gem 'coveralls', require: false, platforms: [:mri]
|
10
|
+
|
11
|
+
gem 'activerecord', '~> 4.1'
|
12
|
+
gem 'ox', '>= 2.1.2', platforms: [:mri, :rbx]
|
9
13
|
end
|
data/Guardfile
CHANGED
data/HISTORY.md
CHANGED
@@ -1,13 +1,30 @@
|
|
1
|
+
# HEAD
|
2
|
+
|
3
|
+
|
4
|
+
# 0.3.0
|
5
|
+
|
6
|
+
* Option to use Ox as a SAX handler instead of Nokogiri [[#49](https://github.com/pauldix/sax-machine/pull/49)]
|
7
|
+
* Bump RSpec to 3.0, convert existing specs
|
8
|
+
|
9
|
+
# 0.2.1
|
10
|
+
|
11
|
+
* Turn on replace_entities on Nokogiri parser [[#40](https://github.com/pauldix/sax-machine/pull/40)]
|
12
|
+
* Provide mass assignment through initialize method [[#38](https://github.com/pauldix/sax-machine/pull/38)]
|
13
|
+
* Bump nokogiri (~> 1.6) and rspec, drop growl dependency
|
14
|
+
* Update 'with' option to allow pattern matching in addition to string matching
|
15
|
+
|
1
16
|
# 0.2.0.rc1
|
2
|
-
|
17
|
+
|
18
|
+
* Try to reduce the number of instances of respond_to? in the code by
|
3
19
|
pulling common uses of it out to methods. [[#32](https://github.com/pauldix/sax-machine/pull/32)]
|
4
20
|
* The parse stack is now composed of simple objects instead of it being
|
5
21
|
an array of arrays. [[#32](https://github.com/pauldix/sax-machine/pull/32)]
|
6
22
|
* Now using an identifier for an empty buffer instead of empty string. [[#32](https://github.com/pauldix/sax-machine/pull/32)]
|
7
|
-
*
|
8
|
-
*
|
9
|
-
*
|
23
|
+
* Clean up several variables that were not being used. [[#32](https://github.com/pauldix/sax-machine/pull/32)]
|
24
|
+
* Encapsulate stack so it's not being exposed as part of the API. [[#32](https://github.com/pauldix/sax-machine/pull/32)]
|
25
|
+
* `cdata_block` is now an alias instead of delegating to characters. [[#32](https://github.com/pauldix/sax-machine/pull/32)]
|
10
26
|
|
11
27
|
# 0.1.0
|
12
|
-
|
13
|
-
*
|
28
|
+
|
29
|
+
* Rename parent to ancestor
|
30
|
+
* Add SAXMachine.configure
|
data/README.md
CHANGED
@@ -1,91 +1,162 @@
|
|
1
|
-
# SAX Machine
|
1
|
+
# SAX Machine
|
2
2
|
|
3
|
-
|
3
|
+
## Status
|
4
|
+
|
5
|
+
[![Gem Version](https://badge.fury.io/rb/sax-machine.svg)](http://badge.fury.io/rb/sax-machine)
|
6
|
+
[![Build Status](https://secure.travis-ci.org/pauldix/sax-machine.svg?branch=master)](http://travis-ci.org/pauldix/sax-machine?branch=master)
|
7
|
+
[![Coverage Status](https://img.shields.io/coveralls/pauldix/sax-machine.svg)](https://coveralls.io/r/pauldix/sax-machine?branch=master)
|
8
|
+
[![Code Climate](https://img.shields.io/codeclimate/github/pauldix/sax-machine.svg)](https://codeclimate.com/github/pauldix/sax-machine)
|
9
|
+
[![Dependencies](https://gemnasium.com/pauldix/sax-machine.svg)](https://gemnasium.com/pauldix/sax-machine)
|
4
10
|
|
5
11
|
## Description
|
6
12
|
|
7
|
-
A declarative SAX parsing library backed by Nokogiri
|
13
|
+
A declarative SAX parsing library backed by Nokogiri or Ox.
|
14
|
+
|
15
|
+
## Installation
|
16
|
+
|
17
|
+
Add this line to your application's Gemfile:
|
18
|
+
|
19
|
+
```ruby
|
20
|
+
gem 'sax-machine'
|
21
|
+
```
|
22
|
+
|
23
|
+
And then execute:
|
24
|
+
|
25
|
+
```bash
|
26
|
+
$ bundle
|
27
|
+
```
|
8
28
|
|
9
29
|
## Usage
|
30
|
+
|
31
|
+
To use **Nokogiri** as a SAX handler:
|
32
|
+
|
10
33
|
```ruby
|
11
34
|
require 'sax-machine'
|
35
|
+
```
|
36
|
+
|
37
|
+
To use **Ox** as a SAX handler:
|
38
|
+
|
39
|
+
Add this line to your application's Gemfile:
|
40
|
+
|
41
|
+
```ruby
|
42
|
+
gem 'ox', '>= 2.1.2'
|
43
|
+
```
|
44
|
+
|
45
|
+
Tell SAXMachine to use Ox:
|
12
46
|
|
13
|
-
|
14
|
-
|
15
|
-
|
47
|
+
```ruby
|
48
|
+
require 'sax-machine'
|
49
|
+
SAXMachine.handler = :ox
|
50
|
+
```
|
51
|
+
|
52
|
+
Please note that this operation is not thread-safe, so it's better to define
|
53
|
+
handler at initialization stage and do not change it during runtime.
|
54
|
+
|
55
|
+
## Examples
|
56
|
+
|
57
|
+
Include `SAXMachine` in any class and define properties to parse:
|
58
|
+
|
59
|
+
```ruby
|
16
60
|
class AtomContent
|
17
61
|
include SAXMachine
|
18
62
|
attribute :type
|
19
63
|
value :text
|
20
64
|
end
|
21
65
|
|
22
|
-
# Class for parsing an atom entry out of a feedburner atom feed
|
23
66
|
class AtomEntry
|
24
67
|
include SAXMachine
|
25
68
|
element :title
|
26
|
-
#
|
27
|
-
element :name, :
|
28
|
-
element "feedburner:origLink", :
|
69
|
+
# The :as argument makes this available through entry.author instead of .name
|
70
|
+
element :name, as: :author
|
71
|
+
element "feedburner:origLink", as: :url
|
29
72
|
element :summary
|
30
|
-
element :content, :
|
73
|
+
element :content, class: AtomContent
|
31
74
|
element :published
|
32
75
|
ancestor :ancestor
|
33
76
|
end
|
34
77
|
|
35
|
-
# Class for parsing Atom feeds
|
36
78
|
class Atom
|
37
79
|
include SAXMachine
|
38
80
|
element :title
|
39
|
-
#
|
40
|
-
#
|
41
|
-
|
42
|
-
|
43
|
-
|
44
|
-
|
81
|
+
# The :with argument means that you only match a link tag
|
82
|
+
# that has an attribute of type: "text/html"
|
83
|
+
element :link, value: :href, as: :url, with: {
|
84
|
+
type: "text/html"
|
85
|
+
}
|
86
|
+
# The :value argument means that instead of setting the value
|
87
|
+
# to the text between the tag, it sets it to the attribute value of :href
|
88
|
+
element :link, value: :href, as: :feed_url, with: {
|
89
|
+
type: "application/atom+xml"
|
90
|
+
}
|
91
|
+
elements :entry, as: :entries, class: AtomEntry
|
45
92
|
end
|
93
|
+
```
|
94
|
+
|
95
|
+
Then parse any XML with your class:
|
46
96
|
|
47
|
-
|
97
|
+
```ruby
|
48
98
|
feed = Atom.parse(xml_text)
|
49
|
-
|
50
|
-
feed.title #
|
51
|
-
feed.url #
|
52
|
-
feed.feed_url #
|
53
|
-
|
54
|
-
feed.entries.first.title #
|
55
|
-
feed.entries.first.author #
|
56
|
-
feed.entries.first.url #
|
57
|
-
feed.entries.first.ancestor #
|
58
|
-
#
|
59
|
-
|
60
|
-
|
61
|
-
|
99
|
+
|
100
|
+
feed.title # Whatever the title of the blog is
|
101
|
+
feed.url # The main URL of the blog
|
102
|
+
feed.feed_url # The URL of the blog feed
|
103
|
+
|
104
|
+
feed.entries.first.title # Title of the first entry
|
105
|
+
feed.entries.first.author # The author of the first entry
|
106
|
+
feed.entries.first.url # Permalink on the blog for this entry
|
107
|
+
feed.entries.first.ancestor # The Atom ancestor
|
108
|
+
feed.entries.first.content # Instance of AtomContent
|
109
|
+
feed.entries.first.content.text # Entry content text
|
110
|
+
```
|
111
|
+
|
112
|
+
You can also use the elements method without specifying a class:
|
113
|
+
|
114
|
+
```ruby
|
115
|
+
class ServiceResponse
|
62
116
|
include SAXMachine
|
63
|
-
elements :message, :
|
117
|
+
elements :message, as: :messages
|
64
118
|
end
|
65
119
|
|
66
|
-
response =
|
67
|
-
response
|
68
|
-
|
120
|
+
response = ServiceResponse.parse("
|
121
|
+
<response>
|
122
|
+
<message>hi</message>
|
123
|
+
<message>world</message>
|
124
|
+
</response>
|
125
|
+
")
|
126
|
+
response.messages.first # hi
|
127
|
+
response.messages.last # world
|
128
|
+
```
|
69
129
|
|
70
|
-
|
130
|
+
To limit conflicts in the class used for mappping, you can use the alternate
|
131
|
+
`SAXMachine.configure` syntax:
|
71
132
|
|
133
|
+
```ruby
|
72
134
|
class X < ActiveRecord::Base
|
73
|
-
#
|
135
|
+
# This way no element, elements or ancestor method will be added to X
|
74
136
|
SAXMachine.configure(X) do |c|
|
75
137
|
c.element :title
|
76
138
|
end
|
77
139
|
end
|
78
140
|
```
|
79
141
|
|
142
|
+
## Contributing
|
143
|
+
|
144
|
+
1. Fork it
|
145
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
146
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
147
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
148
|
+
5. Create new Pull Request
|
149
|
+
|
80
150
|
## LICENSE
|
81
151
|
|
82
152
|
The MIT License
|
83
153
|
|
84
|
-
Copyright (c) 2009-
|
154
|
+
Copyright (c) 2009-2014:
|
85
155
|
|
86
156
|
* [Paul Dix](http://www.pauldix.net)
|
87
157
|
* [Julien Kirch](http://www.archiloque.net)
|
88
158
|
* [Ezekiel Templin](http://zeke.templ.in)
|
159
|
+
* [Dmitry Krasnoukhov](http://krasnoukhov.com)
|
89
160
|
|
90
161
|
Permission is hereby granted, free of charge, to any person obtaining
|
91
162
|
a copy of this software and associated documentation files (the
|
@@ -104,4 +175,4 @@ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
|
104
175
|
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
|
105
176
|
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
106
177
|
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
107
|
-
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
178
|
+
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/Rakefile
CHANGED
data/lib/sax-machine.rb
CHANGED
@@ -1,8 +1,17 @@
|
|
1
1
|
require "sax-machine/version"
|
2
2
|
require "sax-machine/sax_document"
|
3
3
|
require "sax-machine/sax_configure"
|
4
|
-
require "sax-machine/sax_handler"
|
5
4
|
require "sax-machine/sax_config"
|
6
5
|
|
7
6
|
module SAXMachine
|
8
|
-
|
7
|
+
def self.handler
|
8
|
+
@@handler
|
9
|
+
end
|
10
|
+
|
11
|
+
def self.handler=(handler)
|
12
|
+
require "sax-machine/handlers/sax_#{handler}_handler"
|
13
|
+
@@handler = handler
|
14
|
+
end
|
15
|
+
end
|
16
|
+
|
17
|
+
SAXMachine.handler = :nokogiri
|
@@ -1,21 +1,17 @@
|
|
1
1
|
module SAXMachine
|
2
2
|
class SAXConfig
|
3
|
-
|
4
3
|
class AncestorConfig
|
5
4
|
attr_reader :name, :setter
|
6
5
|
|
7
6
|
def initialize(name, options)
|
8
|
-
@name
|
9
|
-
|
10
|
-
@as = options[:as]
|
7
|
+
@name = name.to_s
|
8
|
+
@as = options[:as]
|
11
9
|
@setter = "#{@as}="
|
12
10
|
end
|
13
11
|
|
14
12
|
def column
|
15
13
|
@as || @name.to_sym
|
16
14
|
end
|
17
|
-
|
18
15
|
end
|
19
|
-
|
20
16
|
end
|
21
|
-
end
|
17
|
+
end
|
@@ -1,13 +1,12 @@
|
|
1
1
|
module SAXMachine
|
2
2
|
class SAXConfig
|
3
|
-
|
4
3
|
class AttributeConfig
|
5
4
|
attr_reader :name, :setter
|
6
5
|
|
7
6
|
def initialize(name, options)
|
8
|
-
@name
|
9
|
-
@as
|
10
|
-
@setter
|
7
|
+
@name = name.to_s
|
8
|
+
@as = options[:as]
|
9
|
+
@setter = "#{@as}="
|
11
10
|
@required = options[:required]
|
12
11
|
end
|
13
12
|
|
@@ -16,7 +15,7 @@ module SAXMachine
|
|
16
15
|
end
|
17
16
|
|
18
17
|
def required?
|
19
|
-
|
18
|
+
!!@required
|
20
19
|
end
|
21
20
|
|
22
21
|
def value_from_attrs(attrs)
|
@@ -35,6 +34,5 @@ module SAXMachine
|
|
35
34
|
false
|
36
35
|
end
|
37
36
|
end
|
38
|
-
|
39
37
|
end
|
40
38
|
end
|
@@ -1,20 +1,19 @@
|
|
1
1
|
module SAXMachine
|
2
2
|
class SAXConfig
|
3
|
-
|
4
3
|
class CollectionConfig
|
5
4
|
attr_reader :name
|
6
|
-
|
5
|
+
|
7
6
|
def initialize(name, options)
|
8
7
|
@name = name.to_s
|
9
8
|
@class = options[:class]
|
10
9
|
@as = options[:as].to_s
|
11
10
|
@with = options.fetch(:with, {})
|
12
11
|
end
|
13
|
-
|
12
|
+
|
14
13
|
def accessor
|
15
14
|
as
|
16
15
|
end
|
17
|
-
|
16
|
+
|
18
17
|
def attrs_match?(attrs)
|
19
18
|
@with.all? do |key, value|
|
20
19
|
value === attrs[key.to_s]
|
@@ -23,15 +22,12 @@ module SAXMachine
|
|
23
22
|
|
24
23
|
def data_class
|
25
24
|
@class || @name
|
26
|
-
end
|
27
|
-
|
28
|
-
|
29
|
-
|
25
|
+
end
|
26
|
+
|
27
|
+
protected
|
30
28
|
def as
|
31
29
|
@as
|
32
30
|
end
|
33
|
-
|
34
31
|
end
|
35
|
-
|
36
32
|
end
|
37
33
|
end
|
@@ -1,31 +1,31 @@
|
|
1
1
|
module SAXMachine
|
2
2
|
class SAXConfig
|
3
|
-
|
4
3
|
class ElementConfig
|
5
4
|
attr_reader :name, :setter, :data_class, :collection
|
6
|
-
|
5
|
+
|
7
6
|
def initialize(name, options)
|
8
7
|
@name = name.to_s
|
9
8
|
@with = options.fetch(:with, {})
|
10
9
|
|
11
|
-
if options.has_key?(:value)
|
12
|
-
|
10
|
+
@value = if options.has_key?(:value)
|
11
|
+
options[:value].to_s
|
13
12
|
else
|
14
|
-
|
13
|
+
nil
|
15
14
|
end
|
16
|
-
|
15
|
+
|
17
16
|
@as = options[:as]
|
18
17
|
@collection = options[:collection]
|
19
|
-
|
20
|
-
if @collection
|
21
|
-
|
18
|
+
|
19
|
+
@setter = if @collection
|
20
|
+
"add_#{options[:as]}"
|
22
21
|
else
|
23
|
-
|
22
|
+
"#{@as}="
|
24
23
|
end
|
24
|
+
|
25
25
|
@data_class = options[:class]
|
26
26
|
@required = options[:required]
|
27
27
|
end
|
28
|
-
|
28
|
+
|
29
29
|
def value_configured?
|
30
30
|
!@value.nil?
|
31
31
|
end
|
@@ -39,27 +39,26 @@ module SAXMachine
|
|
39
39
|
end
|
40
40
|
|
41
41
|
def required?
|
42
|
-
|
42
|
+
!!@required
|
43
43
|
end
|
44
44
|
|
45
45
|
def value_from_attrs(attrs)
|
46
46
|
attrs.fetch(@value, nil)
|
47
47
|
end
|
48
|
-
|
48
|
+
|
49
49
|
def attrs_match?(attrs)
|
50
50
|
@with.all? do |key, value|
|
51
51
|
value === attrs[key.to_s]
|
52
52
|
end
|
53
53
|
end
|
54
|
-
|
54
|
+
|
55
55
|
def has_value_and_attrs_match?(attrs)
|
56
56
|
!@value.nil? && attrs_match?(attrs)
|
57
57
|
end
|
58
|
-
|
58
|
+
|
59
59
|
def collection?
|
60
|
-
|
60
|
+
!!@collection
|
61
61
|
end
|
62
62
|
end
|
63
|
-
|
64
63
|
end
|
65
64
|
end
|