saxophone 1.0.0
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/.gitignore +9 -0
- data/.rspec +2 -0
- data/.ruby-version +1 -0
- data/.travis.yml +35 -0
- data/Gemfile +19 -0
- data/README.md +206 -0
- data/Rakefile +7 -0
- data/archive/HISTORY.md +77 -0
- data/lib/saxophone.rb +31 -0
- data/lib/saxophone/config/sax_ancestor.rb +17 -0
- data/lib/saxophone/config/sax_attribute.rb +18 -0
- data/lib/saxophone/config/sax_collection.rb +33 -0
- data/lib/saxophone/config/sax_element.rb +65 -0
- data/lib/saxophone/config/sax_element_value.rb +23 -0
- data/lib/saxophone/handlers/sax_abstract_handler.rb +200 -0
- data/lib/saxophone/handlers/sax_nokogiri_handler.rb +23 -0
- data/lib/saxophone/handlers/sax_oga_handler.rb +39 -0
- data/lib/saxophone/handlers/sax_ox_handler.rb +56 -0
- data/lib/saxophone/sax_config.rb +78 -0
- data/lib/saxophone/sax_configure.rb +33 -0
- data/lib/saxophone/sax_document.rb +137 -0
- data/lib/saxophone/version.rb +3 -0
- data/saxophone.gemspec +19 -0
- data/spec/fixtures/atom-content.html +15 -0
- data/spec/fixtures/atom.xml +165 -0
- data/spec/saxophone/sax_activerecord_spec.rb +33 -0
- data/spec/saxophone/sax_configure_spec.rb +51 -0
- data/spec/saxophone/sax_document_spec.rb +1218 -0
- data/spec/saxophone/sax_include_spec.rb +49 -0
- data/spec/spec_helper.rb +22 -0
- metadata +98 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 57c5242aea2b5daec2f7129d6b12fe56e28e07a8
|
4
|
+
data.tar.gz: c5f4823813e45c56693feeafbb808253367cf533
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 18a39e8330f39c5da059bfcb39f147084d8d707fd6375a9561d4711ce3269dc16a98f860a717d45b181cbd79c555edfc329e7ff80818c0f7e41a65f29a0ce9e6
|
7
|
+
data.tar.gz: 6d4b5006f62bacf0d51e6300ba146083301fcb3922dd960282216272622a130ce7cd6fac88481ad5149ceedf4f0e69c5538decde24cae5fa16ae7944594a3c7c
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.ruby-version
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
2.5.1
|
data/.travis.yml
ADDED
@@ -0,0 +1,35 @@
|
|
1
|
+
language: ruby
|
2
|
+
|
3
|
+
rvm:
|
4
|
+
- 1.9.3
|
5
|
+
- 2.0
|
6
|
+
- 2.1
|
7
|
+
- 2.2
|
8
|
+
- 2.3
|
9
|
+
- 2.4
|
10
|
+
- 2.5
|
11
|
+
- jruby-1.7
|
12
|
+
- rbx-2
|
13
|
+
- ruby-head
|
14
|
+
- jruby-head
|
15
|
+
|
16
|
+
sudo: false
|
17
|
+
|
18
|
+
env:
|
19
|
+
matrix:
|
20
|
+
- HANDLER="nokogiri"
|
21
|
+
- HANDLER="ox"
|
22
|
+
- HANDLER="oga"
|
23
|
+
|
24
|
+
matrix:
|
25
|
+
exclude:
|
26
|
+
- env: HANDLER="ox"
|
27
|
+
rvm: jruby-1.7
|
28
|
+
- env: HANDLER="ox"
|
29
|
+
rvm: jruby-head
|
30
|
+
allow_failures:
|
31
|
+
- env: HANDLER="oga"
|
32
|
+
rvm: jruby-1.7
|
33
|
+
- rvm: rbx-2
|
34
|
+
- rvm: ruby-head
|
35
|
+
- rvm: jruby-head
|
data/Gemfile
ADDED
@@ -0,0 +1,19 @@
|
|
1
|
+
source "http://rubygems.org"
|
2
|
+
|
3
|
+
gemspec
|
4
|
+
|
5
|
+
group :development, :test do
|
6
|
+
gem 'rake'
|
7
|
+
gem 'guard-rspec'
|
8
|
+
gem 'simplecov', require: false, platforms: [:mri]
|
9
|
+
gem 'coveralls', require: false, platforms: [:mri]
|
10
|
+
|
11
|
+
gem 'activerecord', '~> 5.0.0'
|
12
|
+
gem 'nokogiri', '>= 1.8.2'
|
13
|
+
gem 'ox', '>= 2.1.2', platforms: [:mri, :rbx]
|
14
|
+
gem 'oga', '>= 0.3.4'
|
15
|
+
end
|
16
|
+
|
17
|
+
group :test do
|
18
|
+
gem 'sqlite3'
|
19
|
+
end
|
data/README.md
ADDED
@@ -0,0 +1,206 @@
|
|
1
|
+
# Saxophone
|
2
|
+
|
3
|
+
A declarative SAX parsing library backed by Nokogiri, Ox or Oga.
|
4
|
+
|
5
|
+
## Origins
|
6
|
+
|
7
|
+
This repository is a fork of [pauldix/sax-machine](https://github.com/pauldix/sax-machine). We'd like to
|
8
|
+
thank all original authors and contributers for their work on the original repository. However, we have
|
9
|
+
the feeling that the original repository is not being actively maintained anymore - that's why we decided to
|
10
|
+
fork it and continue the work of the original authors in our façon. To make the distinction clear, we
|
11
|
+
renamed the project from that point to `Saxophone`.
|
12
|
+
|
13
|
+
## Installation
|
14
|
+
|
15
|
+
Add this line to your application's Gemfile:
|
16
|
+
|
17
|
+
```ruby
|
18
|
+
gem 'saxophone'
|
19
|
+
```
|
20
|
+
|
21
|
+
And then execute:
|
22
|
+
|
23
|
+
```bash
|
24
|
+
$ bundle
|
25
|
+
```
|
26
|
+
|
27
|
+
## Usage
|
28
|
+
|
29
|
+
Saxophone can use either `nokogiri`, `ox` or `oga` as XML SAX handler.
|
30
|
+
|
31
|
+
To use **Nokogiri** add this line to your Gemfile:
|
32
|
+
|
33
|
+
```ruby
|
34
|
+
gem 'nokogiri', '~> 1.6'
|
35
|
+
```
|
36
|
+
|
37
|
+
To use **Ox** add this line to your Gemfile:
|
38
|
+
|
39
|
+
```ruby
|
40
|
+
gem 'ox', '>= 2.1.2'
|
41
|
+
```
|
42
|
+
|
43
|
+
To use **Oga** add this line to your Gemfile:
|
44
|
+
|
45
|
+
```ruby
|
46
|
+
gem 'oga', '>= 0.2.0'
|
47
|
+
```
|
48
|
+
|
49
|
+
You can also specify which handler to use manually, like this:
|
50
|
+
|
51
|
+
```ruby
|
52
|
+
Saxophone.handler = :nokogiri
|
53
|
+
```
|
54
|
+
|
55
|
+
## Examples
|
56
|
+
|
57
|
+
Include `Saxophone` in any class and define properties to parse:
|
58
|
+
|
59
|
+
```ruby
|
60
|
+
class AtomContent
|
61
|
+
include Saxophone
|
62
|
+
attribute :type
|
63
|
+
value :text
|
64
|
+
end
|
65
|
+
|
66
|
+
class AtomEntry
|
67
|
+
include Saxophone
|
68
|
+
element :title
|
69
|
+
# The :as argument makes this available through entry.author instead of .name
|
70
|
+
element :name, as: :author
|
71
|
+
element "feedburner:origLink", as: :url
|
72
|
+
# The :default argument specifies default value for element when it's missing
|
73
|
+
element :summary, class: String, default: "No summary available"
|
74
|
+
element :content, class: AtomContent
|
75
|
+
element :published
|
76
|
+
ancestor :ancestor
|
77
|
+
end
|
78
|
+
|
79
|
+
class Atom
|
80
|
+
include Saxophone
|
81
|
+
# Use block to modify the returned value
|
82
|
+
# Blocks are working with pretty much everything,
|
83
|
+
# except for `elements` with `class` attribute
|
84
|
+
element :title do |title|
|
85
|
+
title.strip
|
86
|
+
end
|
87
|
+
# The :with argument means that you only match a link tag
|
88
|
+
# that has an attribute of type: "text/html"
|
89
|
+
element :link, value: :href, as: :url, with: {
|
90
|
+
type: "text/html"
|
91
|
+
}
|
92
|
+
# The :value argument means that instead of setting the value
|
93
|
+
# to the text between the tag, it sets it to the attribute value of :href
|
94
|
+
element :link, value: :href, as: :feed_url, with: {
|
95
|
+
type: "application/atom+xml"
|
96
|
+
}
|
97
|
+
elements :entry, as: :entries, class: AtomEntry
|
98
|
+
end
|
99
|
+
```
|
100
|
+
|
101
|
+
Then parse any XML with your class:
|
102
|
+
|
103
|
+
```ruby
|
104
|
+
feed = Atom.parse(xml_text)
|
105
|
+
|
106
|
+
feed.title # Whatever the title of the blog is
|
107
|
+
feed.url # The main URL of the blog
|
108
|
+
feed.feed_url # The URL of the blog feed
|
109
|
+
|
110
|
+
feed.entries.first.title # Title of the first entry
|
111
|
+
feed.entries.first.author # The author of the first entry
|
112
|
+
feed.entries.first.url # Permalink on the blog for this entry
|
113
|
+
feed.entries.first.summary # Returns "No summary available" if summary is missing
|
114
|
+
feed.entries.first.ancestor # The Atom ancestor
|
115
|
+
feed.entries.first.content # Instance of AtomContent
|
116
|
+
feed.entries.first.content.text # Entry content text
|
117
|
+
```
|
118
|
+
|
119
|
+
You can also use the elements method without specifying a class:
|
120
|
+
|
121
|
+
```ruby
|
122
|
+
class ServiceResponse
|
123
|
+
include Saxophone
|
124
|
+
elements :message, as: :messages
|
125
|
+
end
|
126
|
+
|
127
|
+
response = ServiceResponse.parse("
|
128
|
+
<response>
|
129
|
+
<message>hi</message>
|
130
|
+
<message>world</message>
|
131
|
+
</response>
|
132
|
+
")
|
133
|
+
response.messages.first # hi
|
134
|
+
response.messages.last # world
|
135
|
+
```
|
136
|
+
|
137
|
+
To limit conflicts in the class used for mappping, you can use the alternate
|
138
|
+
`Saxophone.configure` syntax:
|
139
|
+
|
140
|
+
```ruby
|
141
|
+
class X < ActiveRecord::Base
|
142
|
+
# This way no element, elements or ancestor method will be added to X
|
143
|
+
Saxophone.configure(X) do |c|
|
144
|
+
c.element :title
|
145
|
+
end
|
146
|
+
end
|
147
|
+
```
|
148
|
+
|
149
|
+
Multiple elements can be mapped to the same alias:
|
150
|
+
|
151
|
+
```ruby
|
152
|
+
class RSSEntry
|
153
|
+
include Saxophone
|
154
|
+
# ...
|
155
|
+
element :pubDate, as: :published
|
156
|
+
element :pubdate, as: :published
|
157
|
+
element :"dc:date", as: :published
|
158
|
+
element :"dc:Date", as: :published
|
159
|
+
element :"dcterms:created", as: :published
|
160
|
+
end
|
161
|
+
```
|
162
|
+
|
163
|
+
If more than one of these elements exists in the source, the value from the *last one* is used. The order of
|
164
|
+
the `element` declarations in the code is unimportant. The order they are encountered while parsing the
|
165
|
+
document determines the value assigned to the alias.
|
166
|
+
|
167
|
+
If an element is defined in the source but is blank (e.g., `<pubDate></pubDate>`), it is ignored, and non-empty one is picked.
|
168
|
+
|
169
|
+
## Contributing
|
170
|
+
|
171
|
+
1. Fork it
|
172
|
+
2. Create your feature branch (`git checkout -b my-new-feature`)
|
173
|
+
3. Commit your changes (`git commit -am 'Add some feature'`)
|
174
|
+
4. Push to the branch (`git push origin my-new-feature`)
|
175
|
+
5. Create new Pull Request
|
176
|
+
|
177
|
+
## LICENSE
|
178
|
+
|
179
|
+
The MIT License
|
180
|
+
|
181
|
+
Copyright (c) 2009-2018:
|
182
|
+
|
183
|
+
* [Paul Dix](http://www.pauldix.net)
|
184
|
+
* [Julien Kirch](http://www.archiloque.net)
|
185
|
+
* [Ezekiel Templin](http://zeke.templ.in)
|
186
|
+
* [Dmitry Krasnoukhov](http://krasnoukhov.com)
|
187
|
+
* [Robin Neumann](https://github.com/neumanrq)
|
188
|
+
|
189
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
190
|
+
a copy of this software and associated documentation files (the
|
191
|
+
'Software'), to deal in the Software without restriction, including
|
192
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
193
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
194
|
+
permit persons to whom the Software is furnished to do so, subject to
|
195
|
+
the following conditions:
|
196
|
+
|
197
|
+
The above copyright notice and this permission notice shall be
|
198
|
+
included in all copies or substantial portions of the Software.
|
199
|
+
|
200
|
+
THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
|
201
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
202
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
203
|
+
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
|
204
|
+
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
205
|
+
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
206
|
+
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/Rakefile
ADDED
data/archive/HISTORY.md
ADDED
@@ -0,0 +1,77 @@
|
|
1
|
+
# Version history of parent gem "sax-machine":
|
2
|
+
|
3
|
+
# 1.3.2
|
4
|
+
|
5
|
+
* Compatibility with Oga 0.3
|
6
|
+
|
7
|
+
# 1.3.1
|
8
|
+
|
9
|
+
* Allow default value to be `false` [[#66](https://github.com/pauldix/sax-machine/pull/66)]
|
10
|
+
* Support adding class to an attribute [[#68](https://github.com/pauldix/sax-machine/pull/68)]
|
11
|
+
* Adjust Ox handler to skip empty text/cdata values
|
12
|
+
|
13
|
+
# 1.3.0
|
14
|
+
|
15
|
+
* Improve block modifiers to support all config options
|
16
|
+
* Make block modifiers run in instance context
|
17
|
+
* Make all handlers support IO as a input
|
18
|
+
|
19
|
+
# 1.2.0
|
20
|
+
|
21
|
+
* Add support for blocks as value modifiers [[#61](https://github.com/pauldix/sax-machine/pull/61)]
|
22
|
+
|
23
|
+
# 1.1.1
|
24
|
+
|
25
|
+
* Fix Nokogiri autoloading [[#60](https://github.com/pauldix/sax-machine/pull/60)]
|
26
|
+
|
27
|
+
# 1.1.0
|
28
|
+
|
29
|
+
* Option to use Oga as a SAX handler
|
30
|
+
|
31
|
+
# 1.0.3
|
32
|
+
|
33
|
+
* Remove missed `nokogiri` reference [[#54](https://github.com/pauldix/sax-machine/pull/54)]
|
34
|
+
* Add support for `Symbol` data type conversion [[#57](https://github.com/pauldix/sax-machine/pull/57)]
|
35
|
+
* Add specs for multiple elements with the same alias [[#53](https://github.com/pauldix/sax-machine/pull/53)]
|
36
|
+
* Various code and documentation enhancements
|
37
|
+
|
38
|
+
# 1.0.2
|
39
|
+
|
40
|
+
* Make sure SAXConfig getters do not modify internal vars. Prevent race conditions
|
41
|
+
|
42
|
+
# 1.0.1
|
43
|
+
|
44
|
+
* Improve normalize_name performance
|
45
|
+
|
46
|
+
# 1.0.0
|
47
|
+
|
48
|
+
* Make `nokogiri` dependency optional
|
49
|
+
* Add :default argument for elements [[#51](https://github.com/pauldix/sax-machine/pull/51)]
|
50
|
+
|
51
|
+
# 0.3.0
|
52
|
+
|
53
|
+
* Option to use Ox as a SAX handler instead of Nokogiri [[#49](https://github.com/pauldix/sax-machine/pull/49)]
|
54
|
+
* Bump RSpec to 3.0, convert existing specs
|
55
|
+
|
56
|
+
# 0.2.1
|
57
|
+
|
58
|
+
* Turn on replace_entities on Nokogiri parser [[#40](https://github.com/pauldix/sax-machine/pull/40)]
|
59
|
+
* Provide mass assignment through initialize method [[#38](https://github.com/pauldix/sax-machine/pull/38)]
|
60
|
+
* Bump nokogiri (~> 1.6) and rspec, drop growl dependency
|
61
|
+
* Update 'with' option to allow pattern matching in addition to string matching
|
62
|
+
|
63
|
+
# 0.2.0.rc1
|
64
|
+
|
65
|
+
* Try to reduce the number of instances of respond_to? in the code by
|
66
|
+
pulling common uses of it out to methods. [[#32](https://github.com/pauldix/sax-machine/pull/32)]
|
67
|
+
* The parse stack is now composed of simple objects instead of it being
|
68
|
+
an array of arrays. [[#32](https://github.com/pauldix/sax-machine/pull/32)]
|
69
|
+
* Now using an identifier for an empty buffer instead of empty string. [[#32](https://github.com/pauldix/sax-machine/pull/32)]
|
70
|
+
* Clean up several variables that were not being used. [[#32](https://github.com/pauldix/sax-machine/pull/32)]
|
71
|
+
* Encapsulate stack so it's not being exposed as part of the API. [[#32](https://github.com/pauldix/sax-machine/pull/32)]
|
72
|
+
* `cdata_block` is now an alias instead of delegating to characters. [[#32](https://github.com/pauldix/sax-machine/pull/32)]
|
73
|
+
|
74
|
+
# 0.1.0
|
75
|
+
|
76
|
+
* Rename parent to ancestor
|
77
|
+
* Add SAXMachine.configure
|
data/lib/saxophone.rb
ADDED
@@ -0,0 +1,31 @@
|
|
1
|
+
require "saxophone/version"
|
2
|
+
require "saxophone/sax_document"
|
3
|
+
require "saxophone/sax_configure"
|
4
|
+
require "saxophone/sax_config"
|
5
|
+
|
6
|
+
module Saxophone
|
7
|
+
def self.handler
|
8
|
+
@@handler ||= nil
|
9
|
+
end
|
10
|
+
|
11
|
+
def self.handler=(handler)
|
12
|
+
if handler
|
13
|
+
require "saxophone/handlers/sax_#{handler}_handler"
|
14
|
+
@@handler = handler
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
# Try handlers
|
20
|
+
[:ox, :oga].each do |handler|
|
21
|
+
begin
|
22
|
+
Saxophone.handler = handler
|
23
|
+
break
|
24
|
+
rescue LoadError
|
25
|
+
end
|
26
|
+
end
|
27
|
+
|
28
|
+
# Still no handler, use Nokogiri
|
29
|
+
if Saxophone.handler.nil?
|
30
|
+
Saxophone.handler = :nokogiri
|
31
|
+
end
|
@@ -0,0 +1,17 @@
|
|
1
|
+
module Saxophone
|
2
|
+
class SAXConfig
|
3
|
+
class AncestorConfig
|
4
|
+
attr_reader :name, :setter
|
5
|
+
|
6
|
+
def initialize(name, options)
|
7
|
+
@name = name.to_s
|
8
|
+
@as = options[:as]
|
9
|
+
@setter = "#{@as}="
|
10
|
+
end
|
11
|
+
|
12
|
+
def column
|
13
|
+
@as || @name.to_sym
|
14
|
+
end
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
@@ -0,0 +1,18 @@
|
|
1
|
+
module Saxophone
|
2
|
+
class SAXConfig
|
3
|
+
class AttributeConfig < ElementValueConfig
|
4
|
+
def value_from_attrs(attrs)
|
5
|
+
attrs.fetch(@name, nil)
|
6
|
+
end
|
7
|
+
|
8
|
+
def attrs_match?(attrs)
|
9
|
+
attrs.key?(@name) || attrs.value?(@name)
|
10
|
+
end
|
11
|
+
alias_method :has_value_and_attrs_match?, :attrs_match?
|
12
|
+
|
13
|
+
def collection?
|
14
|
+
false
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
18
|
+
end
|
@@ -0,0 +1,33 @@
|
|
1
|
+
module Saxophone
|
2
|
+
class SAXConfig
|
3
|
+
class CollectionConfig
|
4
|
+
attr_reader :name
|
5
|
+
|
6
|
+
def initialize(name, options)
|
7
|
+
@name = name.to_s
|
8
|
+
@class = options[:class]
|
9
|
+
@as = options[:as].to_s
|
10
|
+
@with = options.fetch(:with, {})
|
11
|
+
end
|
12
|
+
|
13
|
+
def accessor
|
14
|
+
as
|
15
|
+
end
|
16
|
+
|
17
|
+
def attrs_match?(attrs)
|
18
|
+
@with.all? do |key, value|
|
19
|
+
value === attrs[key.to_s]
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
23
|
+
def data_class
|
24
|
+
@class || @name
|
25
|
+
end
|
26
|
+
|
27
|
+
protected
|
28
|
+
def as
|
29
|
+
@as
|
30
|
+
end
|
31
|
+
end
|
32
|
+
end
|
33
|
+
end
|