julien51-sax-machine 0.0.13
Sign up to get free protection for your applications and to get access to all the features.
- data/README.textile +87 -0
- data/Rakefile +14 -0
- data/lib/sax-machine/sax_collection_config.rb +33 -0
- data/lib/sax-machine/sax_config.rb +38 -0
- data/lib/sax-machine/sax_document.rb +74 -0
- data/lib/sax-machine/sax_element_config.rb +55 -0
- data/lib/sax-machine/sax_handler.rb +116 -0
- data/lib/sax-machine.rb +11 -0
- data/spec/sax-machine/sax_document_spec.rb +362 -0
- data/spec/spec.opts +2 -0
- data/spec/spec_helper.rb +13 -0
- metadata +72 -0
data/README.textile
ADDED
@@ -0,0 +1,87 @@
|
|
1
|
+
h1. SAX Machine
|
2
|
+
|
3
|
+
"http://github.com/pauldix/sax-machine/wikis":http://github.com/pauldix/sax-machine/wikis
|
4
|
+
|
5
|
+
"http://github.com/pauldix/sax-machine/tree/master":http://github.com/pauldix/sax-machine/tree/master
|
6
|
+
|
7
|
+
h2. Description
|
8
|
+
|
9
|
+
A declarative SAX parsing library backed by Nokogiri
|
10
|
+
|
11
|
+
h2. Usage
|
12
|
+
|
13
|
+
<pre>
|
14
|
+
require 'sax-machine'
|
15
|
+
|
16
|
+
# Class for parsing an atom entry out of a feedburner atom feed
|
17
|
+
class AtomEntry
|
18
|
+
include SAXMachine
|
19
|
+
element :title
|
20
|
+
# the :as argument makes this available through atom_entry.author instead of .name
|
21
|
+
element :name, :as => :author
|
22
|
+
element "feedburner:origLink", :as => :url
|
23
|
+
element :summary
|
24
|
+
element :content
|
25
|
+
element :published
|
26
|
+
end
|
27
|
+
|
28
|
+
# Class for parsing Atom feeds
|
29
|
+
class Atom
|
30
|
+
include SAXMachine
|
31
|
+
element :title
|
32
|
+
# the :with argument means that you only match a link tag that has an attribute of :type => "text/html"
|
33
|
+
# the :value argument means that instead of setting the value to the text between the tag,
|
34
|
+
# it sets it to the attribute value of :href
|
35
|
+
element :link, :value => :href, :as => :url, :with => {:type => "text/html"}
|
36
|
+
element :link, :value => :href, :as => :feed_url, :with => {:type => "application/atom+xml"}
|
37
|
+
elements :entry, :as => :entries, :class => AtomEntry
|
38
|
+
end
|
39
|
+
|
40
|
+
# you can then parse like this
|
41
|
+
feed = Atom.parse(xml_text)
|
42
|
+
# then you're ready to rock
|
43
|
+
feed.title # => whatever the title of the blog is
|
44
|
+
feed.url # => the main url of the blog
|
45
|
+
feed.feed_url # => goes to the feedburner feed
|
46
|
+
|
47
|
+
feed.entries.first.title # => title of the first entry
|
48
|
+
feed.entries.first.author # => the author of the first entry
|
49
|
+
feed.entries.first.url # => the permalink on the blog for this entry
|
50
|
+
# etc ...
|
51
|
+
|
52
|
+
# you can also use the elements method without specifying a class like so
|
53
|
+
class SomeServiceResponse
|
54
|
+
elements :message, :as => :messages
|
55
|
+
end
|
56
|
+
|
57
|
+
response = SomeServiceResponse.parse("<response><message>hi</message><message>world</message></response>")
|
58
|
+
response.messages.first # => "hi"
|
59
|
+
response.messages.last # => "world"
|
60
|
+
</pre>
|
61
|
+
|
62
|
+
h2. LICENSE
|
63
|
+
|
64
|
+
(The MIT License)
|
65
|
+
|
66
|
+
Copyright (c) 2009:
|
67
|
+
|
68
|
+
"Paul Dix":http://pauldix.net
|
69
|
+
|
70
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
71
|
+
a copy of this software and associated documentation files (the
|
72
|
+
'Software'), to deal in the Software without restriction, including
|
73
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
74
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
75
|
+
permit persons to whom the Software is furnished to do so, subject to
|
76
|
+
the following conditions:
|
77
|
+
|
78
|
+
The above copyright notice and this permission notice shall be
|
79
|
+
included in all copies or substantial portions of the Software.
|
80
|
+
|
81
|
+
THE SOFTWARE IS PROVIDED 'AS IS', WITHOUT WARRANTY OF ANY KIND,
|
82
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
83
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
|
84
|
+
IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
|
85
|
+
CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
|
86
|
+
TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
|
87
|
+
SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/Rakefile
ADDED
@@ -0,0 +1,14 @@
|
|
1
|
+
require "spec"
|
2
|
+
require "spec/rake/spectask"
|
3
|
+
require 'lib/sax-machine.rb'
|
4
|
+
|
5
|
+
Spec::Rake::SpecTask.new do |t|
|
6
|
+
t.spec_opts = ['--options', "\"#{File.dirname(__FILE__)}/spec/spec.opts\""]
|
7
|
+
t.spec_files = FileList['spec/**/*_spec.rb']
|
8
|
+
end
|
9
|
+
|
10
|
+
task :install do
|
11
|
+
rm_rf "*.gem"
|
12
|
+
puts `gem build sax-machine.gemspec`
|
13
|
+
puts `sudo gem install sax-machine-#{SAXMachine::VERSION}.gem`
|
14
|
+
end
|
@@ -0,0 +1,33 @@
|
|
1
|
+
module SAXMachine
|
2
|
+
class SAXConfig
|
3
|
+
|
4
|
+
class CollectionConfig
|
5
|
+
attr_reader :name
|
6
|
+
|
7
|
+
def initialize(name, options)
|
8
|
+
@name = name.to_s
|
9
|
+
@class = options[:class]
|
10
|
+
@as = options[:as].to_s
|
11
|
+
end
|
12
|
+
|
13
|
+
def handler
|
14
|
+
SAXHandler.new(@class.new)
|
15
|
+
end
|
16
|
+
|
17
|
+
def accessor
|
18
|
+
as
|
19
|
+
end
|
20
|
+
|
21
|
+
protected
|
22
|
+
|
23
|
+
def as
|
24
|
+
@as
|
25
|
+
end
|
26
|
+
|
27
|
+
def class
|
28
|
+
@class || @name
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
end
|
33
|
+
end
|
@@ -0,0 +1,38 @@
|
|
1
|
+
require "sax-machine/sax_element_config"
|
2
|
+
require "sax-machine/sax_collection_config"
|
3
|
+
|
4
|
+
module SAXMachine
|
5
|
+
class SAXConfig
|
6
|
+
def initialize
|
7
|
+
@top_level_elements = []
|
8
|
+
@collection_elements = []
|
9
|
+
end
|
10
|
+
|
11
|
+
def add_top_level_element(name, options)
|
12
|
+
@top_level_elements << ElementConfig.new(name, options)
|
13
|
+
end
|
14
|
+
|
15
|
+
def add_collection_element(name, options)
|
16
|
+
@collection_elements << CollectionConfig.new(name, options)
|
17
|
+
end
|
18
|
+
|
19
|
+
def collection_config(name)
|
20
|
+
@collection_elements.detect { |ce| ce.name.to_s == name.to_s }
|
21
|
+
end
|
22
|
+
|
23
|
+
def element_configs_for_attribute(name, attrs)
|
24
|
+
@top_level_elements.select do |element_config|
|
25
|
+
element_config.name == name &&
|
26
|
+
element_config.has_value_and_attrs_match?(attrs)
|
27
|
+
end
|
28
|
+
end
|
29
|
+
|
30
|
+
def element_config_for_tag(name, attrs)
|
31
|
+
@top_level_elements.detect do |element_config|
|
32
|
+
element_config.name == name &&
|
33
|
+
element_config.attrs_match?(attrs)
|
34
|
+
end
|
35
|
+
end
|
36
|
+
|
37
|
+
end
|
38
|
+
end
|
@@ -0,0 +1,74 @@
|
|
1
|
+
require "nokogiri"
|
2
|
+
|
3
|
+
module SAXMachine
|
4
|
+
|
5
|
+
def self.included(base)
|
6
|
+
base.extend ClassMethods
|
7
|
+
end
|
8
|
+
|
9
|
+
def parse(xml_text)
|
10
|
+
unless @parser
|
11
|
+
sax_handler = SAXHandler.new(self)
|
12
|
+
@parser = Nokogiri::XML::SAX::PushParser.new(sax_handler)
|
13
|
+
end
|
14
|
+
@parser << xml_text
|
15
|
+
self
|
16
|
+
end
|
17
|
+
|
18
|
+
def parse_finish
|
19
|
+
if @parser
|
20
|
+
@parser.finish
|
21
|
+
end
|
22
|
+
self
|
23
|
+
end
|
24
|
+
|
25
|
+
module ClassMethods
|
26
|
+
|
27
|
+
def parse(xml_text)
|
28
|
+
# It might be cleaner to aditionally call parse_finish here, but
|
29
|
+
# then Nokogiri/libxml2 barfs on incomplete documents. Desired
|
30
|
+
# behaviour?
|
31
|
+
new.parse(xml_text)
|
32
|
+
end
|
33
|
+
|
34
|
+
def element(name, options = {})
|
35
|
+
options[:as] ||= name
|
36
|
+
sax_config.add_top_level_element(name, options)
|
37
|
+
|
38
|
+
# we only want to insert the getter and setter if they haven't defined it from elsewhere.
|
39
|
+
# this is how we allow custom parsing behavior. So you could define the setter
|
40
|
+
# and have it parse the string into a date or whatever.
|
41
|
+
attr_reader options[:as] unless instance_methods.include?(options[:as].to_s)
|
42
|
+
attr_writer options[:as] unless instance_methods.include?("#{options[:as]}=")
|
43
|
+
end
|
44
|
+
|
45
|
+
def elements(name, options = {})
|
46
|
+
options[:as] ||= name
|
47
|
+
if options[:class]
|
48
|
+
sax_config.add_collection_element(name, options)
|
49
|
+
else
|
50
|
+
class_eval <<-SRC
|
51
|
+
def add_#{options[:as]}(value)
|
52
|
+
#{options[:as]} << value
|
53
|
+
end
|
54
|
+
SRC
|
55
|
+
sax_config.add_top_level_element(name, options.merge(:collection => true))
|
56
|
+
end
|
57
|
+
|
58
|
+
if !instance_methods.include?(options[:as].to_s)
|
59
|
+
class_eval <<-SRC
|
60
|
+
def #{options[:as]}
|
61
|
+
@#{options[:as]} ||= []
|
62
|
+
end
|
63
|
+
SRC
|
64
|
+
end
|
65
|
+
|
66
|
+
attr_writer options[:as] unless instance_methods.include?("#{options[:as]}=")
|
67
|
+
end
|
68
|
+
|
69
|
+
def sax_config
|
70
|
+
@sax_config ||= SAXConfig.new
|
71
|
+
end
|
72
|
+
end
|
73
|
+
|
74
|
+
end
|
@@ -0,0 +1,55 @@
|
|
1
|
+
module SAXMachine
|
2
|
+
class SAXConfig
|
3
|
+
|
4
|
+
class ElementConfig
|
5
|
+
attr_reader :name, :setter
|
6
|
+
|
7
|
+
def initialize(name, options)
|
8
|
+
@name = name.to_s
|
9
|
+
|
10
|
+
if options.has_key?(:with)
|
11
|
+
# for faster comparisons later
|
12
|
+
@with = options[:with].to_a.flatten.collect {|o| o.to_s}
|
13
|
+
else
|
14
|
+
@with = nil
|
15
|
+
end
|
16
|
+
|
17
|
+
if options.has_key?(:value)
|
18
|
+
@value = options[:value].to_s
|
19
|
+
else
|
20
|
+
@value = nil
|
21
|
+
end
|
22
|
+
|
23
|
+
@as = options[:as]
|
24
|
+
@collection = options[:collection]
|
25
|
+
|
26
|
+
if @collection
|
27
|
+
@setter = "add_#{options[:as]}"
|
28
|
+
else
|
29
|
+
@setter = "#{@as}="
|
30
|
+
end
|
31
|
+
end
|
32
|
+
|
33
|
+
def value_from_attrs(attrs)
|
34
|
+
attrs.index(@value) ? attrs[attrs.index(@value) + 1] : nil
|
35
|
+
end
|
36
|
+
|
37
|
+
def attrs_match?(attrs)
|
38
|
+
if @with
|
39
|
+
@with == (@with & attrs)
|
40
|
+
else
|
41
|
+
true
|
42
|
+
end
|
43
|
+
end
|
44
|
+
|
45
|
+
def has_value_and_attrs_match?(attrs)
|
46
|
+
!@value.nil? && attrs_match?(attrs)
|
47
|
+
end
|
48
|
+
|
49
|
+
def collection?
|
50
|
+
@collection
|
51
|
+
end
|
52
|
+
end
|
53
|
+
|
54
|
+
end
|
55
|
+
end
|
@@ -0,0 +1,116 @@
|
|
1
|
+
require "nokogiri"
|
2
|
+
|
3
|
+
module SAXMachine
|
4
|
+
class SAXHandler < Nokogiri::XML::SAX::Document
|
5
|
+
attr_reader :object
|
6
|
+
|
7
|
+
def initialize(object)
|
8
|
+
@object = object
|
9
|
+
@parsed_configs = {}
|
10
|
+
end
|
11
|
+
|
12
|
+
def characters(string)
|
13
|
+
if parsing_collection?
|
14
|
+
@collection_handler.characters(string)
|
15
|
+
elsif @element_config
|
16
|
+
@value << string
|
17
|
+
end
|
18
|
+
end
|
19
|
+
|
20
|
+
def cdata_block(string)
|
21
|
+
characters(string)
|
22
|
+
end
|
23
|
+
|
24
|
+
def start_element(name, attrs = [])
|
25
|
+
@name = name
|
26
|
+
@attrs = attrs
|
27
|
+
|
28
|
+
if parsing_collection?
|
29
|
+
@collection_handler.start_element(@name, @attrs)
|
30
|
+
|
31
|
+
elsif @collection_config = sax_config.collection_config(@name)
|
32
|
+
@collection_handler = @collection_config.handler
|
33
|
+
@collection_handler.start_element(@name, @attrs)
|
34
|
+
|
35
|
+
elsif (element_configs = sax_config.element_configs_for_attribute(@name, @attrs)).any?
|
36
|
+
parse_element_attributes(element_configs)
|
37
|
+
set_element_config_for_element_value
|
38
|
+
|
39
|
+
else
|
40
|
+
set_element_config_for_element_value
|
41
|
+
end
|
42
|
+
end
|
43
|
+
|
44
|
+
def end_element(name)
|
45
|
+
if parsing_collection? && @collection_config.name == name
|
46
|
+
@object.send(@collection_config.accessor) << @collection_handler.object
|
47
|
+
reset_current_collection
|
48
|
+
|
49
|
+
elsif parsing_collection?
|
50
|
+
@collection_handler.end_element(name)
|
51
|
+
|
52
|
+
elsif characaters_captured? && !parsed_config?
|
53
|
+
mark_as_parsed
|
54
|
+
@object.send(@element_config.setter, @value)
|
55
|
+
end
|
56
|
+
|
57
|
+
reset_current_tag
|
58
|
+
end
|
59
|
+
|
60
|
+
def characaters_captured?
|
61
|
+
!@value.nil? && !@value.empty?
|
62
|
+
end
|
63
|
+
|
64
|
+
def parsing_collection?
|
65
|
+
!@collection_handler.nil?
|
66
|
+
end
|
67
|
+
|
68
|
+
def parse_collection_instance_attributes
|
69
|
+
instance = @collection_handler.object
|
70
|
+
@attrs.each_with_index do |attr_name,index|
|
71
|
+
instance.send("#{attr_name}=", @attrs[index + 1]) if index % 2 == 0 && instance.methods.include?("#{attr_name}=")
|
72
|
+
end
|
73
|
+
end
|
74
|
+
|
75
|
+
def parse_element_attributes(element_configs)
|
76
|
+
element_configs.each do |ec|
|
77
|
+
unless parsed_config?(ec)
|
78
|
+
@object.send(ec.setter, ec.value_from_attrs(@attrs))
|
79
|
+
mark_as_parsed(ec)
|
80
|
+
end
|
81
|
+
end
|
82
|
+
@element_config = nil
|
83
|
+
end
|
84
|
+
|
85
|
+
def set_element_config_for_element_value
|
86
|
+
@value = ""
|
87
|
+
@element_config = sax_config.element_config_for_tag(@name, @attrs)
|
88
|
+
end
|
89
|
+
|
90
|
+
def mark_as_parsed(element_config=nil)
|
91
|
+
element_config ||= @element_config
|
92
|
+
@parsed_configs[element_config] = true unless element_config.collection?
|
93
|
+
end
|
94
|
+
|
95
|
+
def parsed_config?(element_config=nil)
|
96
|
+
element_config ||= @element_config
|
97
|
+
@parsed_configs[element_config]
|
98
|
+
end
|
99
|
+
|
100
|
+
def reset_current_collection
|
101
|
+
@collection_handler = nil
|
102
|
+
@collection_config = nil
|
103
|
+
end
|
104
|
+
|
105
|
+
def reset_current_tag
|
106
|
+
@name = nil
|
107
|
+
@attrs = nil
|
108
|
+
@value = nil
|
109
|
+
@element_config = nil
|
110
|
+
end
|
111
|
+
|
112
|
+
def sax_config
|
113
|
+
@object.class.sax_config
|
114
|
+
end
|
115
|
+
end
|
116
|
+
end
|
data/lib/sax-machine.rb
ADDED
@@ -0,0 +1,11 @@
|
|
1
|
+
require "rubygems"
|
2
|
+
|
3
|
+
$LOAD_PATH.unshift(File.expand_path(File.dirname(__FILE__))) unless $LOAD_PATH.include?(File.expand_path(File.dirname(__FILE__)))
|
4
|
+
|
5
|
+
require "sax-machine/sax_document"
|
6
|
+
require "sax-machine/sax_handler"
|
7
|
+
require "sax-machine/sax_config"
|
8
|
+
|
9
|
+
module SAXMachine
|
10
|
+
VERSION = "0.0.13"
|
11
|
+
end
|
@@ -0,0 +1,362 @@
|
|
1
|
+
require File.dirname(__FILE__) + '/../spec_helper'
|
2
|
+
|
3
|
+
describe "SAXMachine" do
|
4
|
+
describe "element" do
|
5
|
+
describe "when parsing a single element" do
|
6
|
+
before :each do
|
7
|
+
@klass = Class.new do
|
8
|
+
include SAXMachine
|
9
|
+
element :title
|
10
|
+
end
|
11
|
+
end
|
12
|
+
|
13
|
+
it "should provide an accessor" do
|
14
|
+
document = @klass.new
|
15
|
+
document.title = "Title"
|
16
|
+
document.title.should == "Title"
|
17
|
+
end
|
18
|
+
|
19
|
+
it "should not overwrite the setter if there is already one present" do
|
20
|
+
@klass = Class.new do
|
21
|
+
def title=(val)
|
22
|
+
@title = "#{val} **"
|
23
|
+
end
|
24
|
+
include SAXMachine
|
25
|
+
element :title
|
26
|
+
end
|
27
|
+
document = @klass.new
|
28
|
+
document.title = "Title"
|
29
|
+
document.title.should == "Title **"
|
30
|
+
end
|
31
|
+
|
32
|
+
it "should not overwrite the accessor when the element is not present" do
|
33
|
+
document = @klass.new
|
34
|
+
document.title = "Title"
|
35
|
+
document.parse("<foo></foo>")
|
36
|
+
document.title.should == "Title"
|
37
|
+
end
|
38
|
+
|
39
|
+
it "should overwrite the value when the element is present" do
|
40
|
+
document = @klass.new
|
41
|
+
document.title = "Old title"
|
42
|
+
document.parse("<title>New title</title>")
|
43
|
+
document.title.should == "New title"
|
44
|
+
end
|
45
|
+
|
46
|
+
it "should save the element text into an accessor" do
|
47
|
+
document = @klass.parse("<title>My Title</title>")
|
48
|
+
document.title.should == "My Title"
|
49
|
+
end
|
50
|
+
|
51
|
+
it "should save cdata into an accessor" do
|
52
|
+
document = @klass.parse("<title><![CDATA[A Title]]></title>")
|
53
|
+
document.title.should == "A Title"
|
54
|
+
end
|
55
|
+
|
56
|
+
it "should save the element text into an accessor when there are multiple elements" do
|
57
|
+
document = @klass.parse("<xml><title>My Title</title><foo>bar</foo></xml>")
|
58
|
+
document.title.should == "My Title"
|
59
|
+
end
|
60
|
+
|
61
|
+
it "should save the first element text when there are multiple of the same element" do
|
62
|
+
document = @klass.parse("<xml><title>My Title</title><title>bar</title></xml>")
|
63
|
+
document.title.should == "My Title"
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
describe "when parsing multiple elements" do
|
68
|
+
before :each do
|
69
|
+
@klass = Class.new do
|
70
|
+
include SAXMachine
|
71
|
+
element :title
|
72
|
+
element :name
|
73
|
+
end
|
74
|
+
end
|
75
|
+
|
76
|
+
it "should save the element text for a second tag" do
|
77
|
+
document = @klass.parse("<xml><title>My Title</title><name>Paul</name></xml>")
|
78
|
+
document.name.should == "Paul"
|
79
|
+
document.title.should == "My Title"
|
80
|
+
end
|
81
|
+
end
|
82
|
+
|
83
|
+
describe "when using options for parsing elements" do
|
84
|
+
describe "using the 'as' option" do
|
85
|
+
before :each do
|
86
|
+
@klass = Class.new do
|
87
|
+
include SAXMachine
|
88
|
+
element :description, :as => :summary
|
89
|
+
end
|
90
|
+
end
|
91
|
+
|
92
|
+
it "should provide an accessor using the 'as' name" do
|
93
|
+
document = @klass.new
|
94
|
+
document.summary = "a small summary"
|
95
|
+
document.summary.should == "a small summary"
|
96
|
+
end
|
97
|
+
|
98
|
+
it "should save the element text into the 'as' accessor" do
|
99
|
+
document = @klass.parse("<description>here is a description</description>")
|
100
|
+
document.summary.should == "here is a description"
|
101
|
+
end
|
102
|
+
end
|
103
|
+
|
104
|
+
describe "using the :with option" do
|
105
|
+
describe "and the :value option" do
|
106
|
+
before :each do
|
107
|
+
@klass = Class.new do
|
108
|
+
include SAXMachine
|
109
|
+
element :link, :value => :href, :with => {:foo => "bar"}
|
110
|
+
end
|
111
|
+
end
|
112
|
+
|
113
|
+
it "should save the value of a matching element" do
|
114
|
+
document = @klass.parse("<link href='test' foo='bar'>asdf</link>")
|
115
|
+
document.link.should == "test"
|
116
|
+
end
|
117
|
+
|
118
|
+
it "should save the value of the first matching element" do
|
119
|
+
document = @klass.parse("<xml><link href='first' foo='bar' /><link href='second' foo='bar' /></xml>")
|
120
|
+
document.link.should == "first"
|
121
|
+
end
|
122
|
+
|
123
|
+
describe "and the :as option" do
|
124
|
+
before :each do
|
125
|
+
@klass = Class.new do
|
126
|
+
include SAXMachine
|
127
|
+
element :link, :value => :href, :as => :url, :with => {:foo => "bar"}
|
128
|
+
element :link, :value => :href, :as => :second_url, :with => {:asdf => "jkl"}
|
129
|
+
end
|
130
|
+
end
|
131
|
+
|
132
|
+
it "should save the value of the first matching element" do
|
133
|
+
document = @klass.parse("<xml><link href='first' foo='bar' /><link href='second' asdf='jkl' /><link href='second' foo='bar' /></xml>")
|
134
|
+
document.url.should == "first"
|
135
|
+
document.second_url.should == "second"
|
136
|
+
end
|
137
|
+
end
|
138
|
+
end
|
139
|
+
|
140
|
+
describe "with only one element" do
|
141
|
+
before :each do
|
142
|
+
@klass = Class.new do
|
143
|
+
include SAXMachine
|
144
|
+
element :link, :with => {:foo => "bar"}
|
145
|
+
end
|
146
|
+
end
|
147
|
+
|
148
|
+
it "should save the text of an element that has matching attributes" do
|
149
|
+
document = @klass.parse("<link foo=\"bar\">match</link>")
|
150
|
+
document.link.should == "match"
|
151
|
+
end
|
152
|
+
|
153
|
+
it "should not save the text of an element that doesn't have matching attributes" do
|
154
|
+
document = @klass.parse("<link>no match</link>")
|
155
|
+
document.link.should be_nil
|
156
|
+
end
|
157
|
+
|
158
|
+
it "should save the text of an element that has matching attributes when it is the second of that type" do
|
159
|
+
document = @klass.parse("<xml><link>no match</link><link foo=\"bar\">match</link></xml>")
|
160
|
+
document.link.should == "match"
|
161
|
+
end
|
162
|
+
|
163
|
+
it "should save the text of an element that has matching attributes plus a few more" do
|
164
|
+
document = @klass.parse("<xml><link>no match</link><link asdf='jkl' foo='bar'>match</link>")
|
165
|
+
document.link.should == "match"
|
166
|
+
end
|
167
|
+
end
|
168
|
+
|
169
|
+
describe "with multiple elements of same tag" do
|
170
|
+
before :each do
|
171
|
+
@klass = Class.new do
|
172
|
+
include SAXMachine
|
173
|
+
element :link, :as => :first, :with => {:foo => "bar"}
|
174
|
+
element :link, :as => :second, :with => {:asdf => "jkl"}
|
175
|
+
end
|
176
|
+
end
|
177
|
+
|
178
|
+
it "should match the first element" do
|
179
|
+
document = @klass.parse("<xml><link>no match</link><link foo=\"bar\">first match</link><link>no match</link></xml>")
|
180
|
+
document.first.should == "first match"
|
181
|
+
end
|
182
|
+
|
183
|
+
it "should match the second element" do
|
184
|
+
document = @klass.parse("<xml><link>no match</link><link foo='bar'>first match</link><link asdf='jkl'>second match</link><link>hi</link></xml>")
|
185
|
+
document.second.should == "second match"
|
186
|
+
end
|
187
|
+
end
|
188
|
+
end # using the 'with' option
|
189
|
+
|
190
|
+
describe "using the 'value' option" do
|
191
|
+
before :each do
|
192
|
+
@klass = Class.new do
|
193
|
+
include SAXMachine
|
194
|
+
element :link, :value => :foo
|
195
|
+
end
|
196
|
+
end
|
197
|
+
|
198
|
+
it "should save the attribute value" do
|
199
|
+
document = @klass.parse("<link foo='test'>hello</link>")
|
200
|
+
document.link.should == 'test'
|
201
|
+
end
|
202
|
+
|
203
|
+
it "should save the attribute value when there is no text enclosed by the tag" do
|
204
|
+
document = @klass.parse("<link foo='test'></link>")
|
205
|
+
document.link.should == 'test'
|
206
|
+
end
|
207
|
+
|
208
|
+
it "should save the attribute value when the tag close is in the open" do
|
209
|
+
document = @klass.parse("<link foo='test'/>")
|
210
|
+
document.link.should == 'test'
|
211
|
+
end
|
212
|
+
|
213
|
+
it "should save two different attribute values on a single tag" do
|
214
|
+
@klass = Class.new do
|
215
|
+
include SAXMachine
|
216
|
+
element :link, :value => :foo, :as => :first
|
217
|
+
element :link, :value => :bar, :as => :second
|
218
|
+
end
|
219
|
+
document = @klass.parse("<link foo='foo value' bar='bar value'></link>")
|
220
|
+
document.first.should == "foo value"
|
221
|
+
document.second.should == "bar value"
|
222
|
+
end
|
223
|
+
|
224
|
+
it "should not fail if one of the attribute hasn't been defined" do
|
225
|
+
@klass = Class.new do
|
226
|
+
include SAXMachine
|
227
|
+
element :link, :value => :foo, :as => :first
|
228
|
+
element :link, :value => :bar, :as => :second
|
229
|
+
end
|
230
|
+
document = @klass.parse("<link foo='foo value'></link>")
|
231
|
+
document.first.should == "foo value"
|
232
|
+
document.second.should be_nil
|
233
|
+
end
|
234
|
+
end
|
235
|
+
|
236
|
+
describe "when desiring both the content and attributes of an element" do
|
237
|
+
before :each do
|
238
|
+
@klass = Class.new do
|
239
|
+
include SAXMachine
|
240
|
+
element :link
|
241
|
+
element :link, :value => :foo, :as => :link_foo
|
242
|
+
element :link, :value => :bar, :as => :link_bar
|
243
|
+
end
|
244
|
+
end
|
245
|
+
|
246
|
+
it "should parse the element and attribute values" do
|
247
|
+
document = @klass.parse("<link foo='test1' bar='test2'>hello</link>")
|
248
|
+
document.link.should == 'hello'
|
249
|
+
document.link_foo.should == 'test1'
|
250
|
+
document.link_bar.should == 'test2'
|
251
|
+
end
|
252
|
+
end
|
253
|
+
|
254
|
+
end
|
255
|
+
end
|
256
|
+
|
257
|
+
describe "elements" do
|
258
|
+
describe "when parsing multiple elements" do
|
259
|
+
before :each do
|
260
|
+
@klass = Class.new do
|
261
|
+
include SAXMachine
|
262
|
+
elements :entry, :as => :entries
|
263
|
+
end
|
264
|
+
end
|
265
|
+
|
266
|
+
it "should provide a collection accessor" do
|
267
|
+
document = @klass.new
|
268
|
+
document.entries << :foo
|
269
|
+
document.entries.should == [:foo]
|
270
|
+
end
|
271
|
+
|
272
|
+
it "should parse a single element" do
|
273
|
+
document = @klass.parse("<entry>hello</entry>")
|
274
|
+
document.entries.should == ["hello"]
|
275
|
+
end
|
276
|
+
|
277
|
+
it "should parse multiple elements" do
|
278
|
+
document = @klass.parse("<xml><entry>hello</entry><entry>world</entry></xml>")
|
279
|
+
document.entries.should == ["hello", "world"]
|
280
|
+
end
|
281
|
+
|
282
|
+
it "should parse multiple elements when taking an attribute value" do
|
283
|
+
attribute_klass = Class.new do
|
284
|
+
include SAXMachine
|
285
|
+
elements :entry, :as => :entries, :value => :foo
|
286
|
+
end
|
287
|
+
doc = attribute_klass.parse("<xml><entry foo='asdf' /><entry foo='jkl' /></xml>")
|
288
|
+
doc.entries.should == ["asdf", "jkl"]
|
289
|
+
end
|
290
|
+
end
|
291
|
+
|
292
|
+
describe "when using the class option" do
|
293
|
+
before :each do
|
294
|
+
class Foo
|
295
|
+
include SAXMachine
|
296
|
+
element :title
|
297
|
+
end
|
298
|
+
@klass = Class.new do
|
299
|
+
include SAXMachine
|
300
|
+
elements :entry, :as => :entries, :class => Foo
|
301
|
+
end
|
302
|
+
end
|
303
|
+
|
304
|
+
it "should parse a single element with children" do
|
305
|
+
document = @klass.parse("<entry><title>a title</title></entry>")
|
306
|
+
document.entries.size.should == 1
|
307
|
+
document.entries.first.title.should == "a title"
|
308
|
+
end
|
309
|
+
|
310
|
+
it "should parse multiple elements with children" do
|
311
|
+
document = @klass.parse("<xml><entry><title>title 1</title></entry><entry><title>title 2</title></entry></xml>")
|
312
|
+
document.entries.size.should == 2
|
313
|
+
document.entries.first.title.should == "title 1"
|
314
|
+
document.entries.last.title.should == "title 2"
|
315
|
+
end
|
316
|
+
|
317
|
+
it "should not parse a top level element that is specified only in a child" do
|
318
|
+
document = @klass.parse("<xml><title>no parse</title><entry><title>correct title</title></entry></xml>")
|
319
|
+
document.entries.size.should == 1
|
320
|
+
document.entries.first.title.should == "correct title"
|
321
|
+
end
|
322
|
+
|
323
|
+
it "should parse out an attribute value from the tag that starts the collection" do
|
324
|
+
class Foo
|
325
|
+
element :entry, :value => :href, :as => :url
|
326
|
+
end
|
327
|
+
document = @klass.parse("<xml><entry href='http://pauldix.net'><title>paul</title></entry></xml>")
|
328
|
+
document.entries.size.should == 1
|
329
|
+
document.entries.first.title.should == "paul"
|
330
|
+
document.entries.first.url.should == "http://pauldix.net"
|
331
|
+
end
|
332
|
+
end
|
333
|
+
end
|
334
|
+
|
335
|
+
describe "full example" do
|
336
|
+
before :each do
|
337
|
+
@xml = File.read('spec/sax-machine/atom.xml')
|
338
|
+
class AtomEntry
|
339
|
+
include SAXMachine
|
340
|
+
element :title
|
341
|
+
element :name, :as => :author
|
342
|
+
element "feedburner:origLink", :as => :url
|
343
|
+
element :summary
|
344
|
+
element :content
|
345
|
+
element :published
|
346
|
+
end
|
347
|
+
|
348
|
+
class Atom
|
349
|
+
include SAXMachine
|
350
|
+
element :title
|
351
|
+
element :link, :value => :href, :as => :url, :with => {:type => "text/html"}
|
352
|
+
element :link, :value => :href, :as => :feed_url, :with => {:type => "application/atom+xml"}
|
353
|
+
elements :entry, :as => :entries, :class => AtomEntry
|
354
|
+
end
|
355
|
+
end # before
|
356
|
+
|
357
|
+
it "should parse the url" do
|
358
|
+
f = Atom.parse(@xml)
|
359
|
+
f.url.should == "http://www.pauldix.net/"
|
360
|
+
end
|
361
|
+
end
|
362
|
+
end
|
data/spec/spec.opts
ADDED
data/spec/spec_helper.rb
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
require "rubygems"
|
2
|
+
require "spec"
|
3
|
+
|
4
|
+
# gem install redgreen for colored test output
|
5
|
+
begin require "redgreen" unless ENV['TM_CURRENT_LINE']; rescue LoadError; end
|
6
|
+
|
7
|
+
path = File.expand_path(File.dirname(__FILE__) + "/../lib/")
|
8
|
+
$LOAD_PATH.unshift(path) unless $LOAD_PATH.include?(path)
|
9
|
+
|
10
|
+
require "lib/sax-machine"
|
11
|
+
|
12
|
+
# Spec::Runner.configure do |config|
|
13
|
+
# end
|
metadata
ADDED
@@ -0,0 +1,72 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: julien51-sax-machine
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.0.13
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Paul Dix
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2009-01-13 00:00:00 -08:00
|
13
|
+
default_executable:
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: nokogiri
|
17
|
+
type: :runtime
|
18
|
+
version_requirement:
|
19
|
+
version_requirements: !ruby/object:Gem::Requirement
|
20
|
+
requirements:
|
21
|
+
- - ">"
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: 0.0.0
|
24
|
+
version:
|
25
|
+
description:
|
26
|
+
email: paul@pauldix.net
|
27
|
+
executables: []
|
28
|
+
|
29
|
+
extensions: []
|
30
|
+
|
31
|
+
extra_rdoc_files: []
|
32
|
+
|
33
|
+
files:
|
34
|
+
- lib/sax-machine.rb
|
35
|
+
- lib/sax-machine/sax_config.rb
|
36
|
+
- lib/sax-machine/sax_collection_config.rb
|
37
|
+
- lib/sax-machine/sax_element_config.rb
|
38
|
+
- lib/sax-machine/sax_document.rb
|
39
|
+
- lib/sax-machine/sax_handler.rb
|
40
|
+
- README.textile
|
41
|
+
- Rakefile
|
42
|
+
- spec/spec.opts
|
43
|
+
- spec/spec_helper.rb
|
44
|
+
- spec/sax-machine/sax_document_spec.rb
|
45
|
+
has_rdoc: false
|
46
|
+
homepage: http://github.com/pauldix/sax-machine
|
47
|
+
post_install_message:
|
48
|
+
rdoc_options: []
|
49
|
+
|
50
|
+
require_paths:
|
51
|
+
- lib
|
52
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
53
|
+
requirements:
|
54
|
+
- - ">="
|
55
|
+
- !ruby/object:Gem::Version
|
56
|
+
version: "0"
|
57
|
+
version:
|
58
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
59
|
+
requirements:
|
60
|
+
- - ">="
|
61
|
+
- !ruby/object:Gem::Version
|
62
|
+
version: "0"
|
63
|
+
version:
|
64
|
+
requirements: []
|
65
|
+
|
66
|
+
rubyforge_project:
|
67
|
+
rubygems_version: 1.2.0
|
68
|
+
signing_key:
|
69
|
+
specification_version: 2
|
70
|
+
summary: Declarative SAX Parsing with Nokogiri
|
71
|
+
test_files: []
|
72
|
+
|