multi_xml 0.4.0 → 0.4.1
Sign up to get free protection for your applications and to get access to all the features.
Potentially problematic release.
This version of multi_xml might be problematic. Click here for more details.
- data/.travis.yml +0 -1
- data/Gemfile +3 -3
- data/README.md +6 -2
- data/lib/multi_xml.rb +6 -11
- data/lib/multi_xml/parsers/ox.rb +79 -31
- data/lib/multi_xml/version.rb +1 -1
- data/multi_xml.gemspec +3 -1
- data/spec/speed.rb +63 -0
- metadata +135 -62
data/.travis.yml
CHANGED
data/Gemfile
CHANGED
@@ -1,9 +1,9 @@
|
|
1
1
|
source 'http://rubygems.org'
|
2
2
|
|
3
3
|
group :development, :test do
|
4
|
-
gem 'libxml-ruby',
|
5
|
-
gem 'nokogiri',
|
6
|
-
gem 'ox',
|
4
|
+
gem 'libxml-ruby', '~> 2.0', :require => nil, :platforms => :mri
|
5
|
+
gem 'nokogiri', '~> 1.4', :require => nil
|
6
|
+
gem 'ox', '~> 1.3', :require => nil
|
7
7
|
end
|
8
8
|
|
9
9
|
gemspec
|
data/README.md
CHANGED
@@ -8,7 +8,7 @@ A generic swappable back-end for XML parsing
|
|
8
8
|
[http://rdoc.info/gems/multi_xml](http://rdoc.info/gems/multi_xml)
|
9
9
|
|
10
10
|
## <a name="ci">Continuous Integration</a>
|
11
|
-
[![Build Status](https://travis-ci.org/sferik/multi_xml.png)](http://travis-ci.org/sferik/multi_xml)
|
11
|
+
[![Build Status](https://secure.travis-ci.org/sferik/multi_xml.png)](http://travis-ci.org/sferik/multi_xml)
|
12
12
|
|
13
13
|
## <a name="examples">Usage Examples</a>
|
14
14
|
Lots of Ruby libraries utilize XML parsing in some form, and everyone has their
|
@@ -26,6 +26,10 @@ library. You use it like so:
|
|
26
26
|
MultiXml.parser = MultiXml::Parsers::Nokogiri # Same as above
|
27
27
|
MultiXml.parse('<tag>This is the contents</tag>') # Parsed using Nokogiri
|
28
28
|
|
29
|
+
MultiXml.parser = :ox
|
30
|
+
MultiXml.parser = MultiXml::Parsers::Ox # Same as above
|
31
|
+
MultiXml.parse('<tag>This is the contents</tag>') # Parsed using Ox
|
32
|
+
|
29
33
|
MultiXml.parser = :rexml
|
30
34
|
MultiXml.parser = MultiXml::Parsers::Rexml # Same as above
|
31
35
|
MultiXml.parse('<tag>This is the contents</tag>') # Parsed using REXML
|
@@ -35,7 +39,7 @@ responds to <tt>.parse</tt> at the class level.
|
|
35
39
|
|
36
40
|
MultiXML tries to have intelligent defaulting. That is, if you have any of the supported parsers
|
37
41
|
already loaded, it will utilize them before attempting to load any. When loading, libraries are
|
38
|
-
ordered by speed: first LibXML, then Nokogiri, then REXML.
|
42
|
+
ordered by speed: first LibXML, then Nokogiri, then Ox, then REXML.
|
39
43
|
|
40
44
|
## <a name="contributing">Contributing</a>
|
41
45
|
In the spirit of [free
|
data/lib/multi_xml.rb
CHANGED
@@ -56,6 +56,7 @@ module MultiXml
|
|
56
56
|
def default_parser
|
57
57
|
return :libxml if defined?(::LibXML)
|
58
58
|
return :nokogiri if defined?(::Nokogiri)
|
59
|
+
return :ox if defined?(::Ox)
|
59
60
|
|
60
61
|
REQUIREMENT_MAP.each do |(library, parser)|
|
61
62
|
begin
|
@@ -95,20 +96,14 @@ module MultiXml
|
|
95
96
|
xml ||= ''
|
96
97
|
|
97
98
|
xml.strip! if xml.respond_to?(:strip!)
|
98
|
-
|
99
99
|
begin
|
100
|
-
|
101
|
-
raw_hash = parser.parse(xml)
|
102
|
-
else
|
103
|
-
xml = StringIO.new(xml) unless xml.respond_to?(:read)
|
100
|
+
xml = StringIO.new(xml) unless xml.respond_to?(:read)
|
104
101
|
|
105
|
-
|
106
|
-
|
107
|
-
|
102
|
+
char = xml.getc
|
103
|
+
return {} if char.nil?
|
104
|
+
xml.ungetc(char)
|
108
105
|
|
109
|
-
|
110
|
-
end
|
111
|
-
hash = typecast_xml_value(undasherize_keys(raw_hash)) || {}
|
106
|
+
hash = typecast_xml_value(undasherize_keys(parser.parse(xml))) || {}
|
112
107
|
rescue parser.parse_error => error
|
113
108
|
raise ParseError, error.to_s, error.backtrace
|
114
109
|
end
|
data/lib/multi_xml/parsers/ox.rb
CHANGED
@@ -1,5 +1,23 @@
|
|
1
1
|
require 'ox' unless defined?(Ox)
|
2
2
|
|
3
|
+
# Each MultiXml parser is expected to parse an XML document into a Hash. The
|
4
|
+
# conversion rules are:
|
5
|
+
#
|
6
|
+
# - Each document starts out as an empty Hash.
|
7
|
+
#
|
8
|
+
# - Reading an element created an entry in the parent Hash that has a key of
|
9
|
+
# the element name and a value of a Hash with attributes as key value
|
10
|
+
# pairs. Children are added as described by this rule.
|
11
|
+
#
|
12
|
+
# - Text and CDATE is stored in the parent element Hash with a key of
|
13
|
+
# '__content__' and a value of the text itself.
|
14
|
+
#
|
15
|
+
# - If a key already exists in the Hash then the value associated with the key
|
16
|
+
# is converted to an Array with the old and new value in it.
|
17
|
+
#
|
18
|
+
# - Other elements such as the xml prolog, doctype, and comments are ignored.
|
19
|
+
#
|
20
|
+
|
3
21
|
module MultiXml
|
4
22
|
module Parsers
|
5
23
|
module Ox #:nodoc:
|
@@ -10,40 +28,70 @@ module MultiXml
|
|
10
28
|
Exception
|
11
29
|
end
|
12
30
|
|
13
|
-
def parse(
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
h
|
31
|
+
def parse(io)
|
32
|
+
handler = Handler.new
|
33
|
+
::Ox.sax_parse(handler, io, :convert_special => true)
|
34
|
+
handler.doc
|
18
35
|
end
|
19
36
|
|
20
|
-
|
21
|
-
|
22
|
-
|
23
|
-
|
24
|
-
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
|
37
|
+
class Handler
|
38
|
+
attr_accessor :stack
|
39
|
+
|
40
|
+
def initialize()
|
41
|
+
@stack = []
|
42
|
+
end
|
43
|
+
|
44
|
+
def doc
|
45
|
+
@stack[0]
|
46
|
+
end
|
47
|
+
|
48
|
+
def attr(name, value)
|
49
|
+
unless @stack.empty?
|
50
|
+
append(name, value)
|
32
51
|
end
|
33
52
|
end
|
34
|
-
|
35
|
-
|
36
|
-
|
37
|
-
|
38
|
-
|
39
|
-
|
53
|
+
|
54
|
+
def text(value)
|
55
|
+
append('__content__', value)
|
56
|
+
end
|
57
|
+
|
58
|
+
def cdata(value)
|
59
|
+
append('__content__', value)
|
60
|
+
end
|
61
|
+
|
62
|
+
def start_element(name)
|
63
|
+
if @stack.empty?
|
64
|
+
@stack.push(Hash.new)
|
65
|
+
end
|
66
|
+
h = Hash.new
|
67
|
+
append(name, h)
|
68
|
+
@stack.push(h)
|
69
|
+
end
|
70
|
+
|
71
|
+
def end_element(name)
|
72
|
+
@stack.pop()
|
73
|
+
end
|
74
|
+
|
75
|
+
def error(message, line, column)
|
76
|
+
raise Exception.new("#{message} at #{line}:#{column}")
|
77
|
+
end
|
78
|
+
|
79
|
+
def append(key, value)
|
80
|
+
key = key.to_s
|
81
|
+
h = @stack.last
|
82
|
+
if h.has_key?(key)
|
83
|
+
v = h[key]
|
84
|
+
if v.is_a?(Array)
|
85
|
+
v << value
|
86
|
+
else
|
87
|
+
h[key] = [v, value]
|
88
|
+
end
|
89
|
+
else
|
90
|
+
h[key] = value
|
91
|
+
end
|
40
92
|
end
|
41
|
-
end
|
42
|
-
|
43
|
-
def string_parser?
|
44
|
-
true
|
45
|
-
end
|
46
93
|
|
47
|
-
|
48
|
-
|
49
|
-
end
|
94
|
+
end # Handler
|
95
|
+
end # Ox
|
96
|
+
end # Parsers
|
97
|
+
end # MultiXml
|
data/lib/multi_xml/version.rb
CHANGED
data/multi_xml.gemspec
CHANGED
@@ -2,14 +2,16 @@
|
|
2
2
|
require File.expand_path('../lib/multi_xml/version', __FILE__)
|
3
3
|
|
4
4
|
Gem::Specification.new do |gem|
|
5
|
+
gem.add_development_dependency 'libxml-ruby', '~> 2.0' unless RUBY_PLATFORM == 'java'
|
5
6
|
gem.add_development_dependency 'nokogiri', '~> 1.4'
|
7
|
+
gem.add_development_dependency 'ox', '~> 1.3'
|
6
8
|
gem.add_development_dependency 'rake', '~> 0.9'
|
7
9
|
gem.add_development_dependency 'rdiscount', '~> 1.6'
|
8
10
|
gem.add_development_dependency 'rspec', '~> 2.6'
|
9
11
|
gem.add_development_dependency 'simplecov', '~> 0.4'
|
10
12
|
gem.add_development_dependency 'yard', '~> 0.7'
|
11
13
|
gem.author = "Erik Michaels-Ober"
|
12
|
-
gem.description = %q{A gem to provide swappable XML backends utilizing LibXML, Nokogiri, or REXML.}
|
14
|
+
gem.description = %q{A gem to provide swappable XML backends utilizing LibXML, Nokogiri, Ox, or REXML.}
|
13
15
|
gem.email = 'sferik@gmail.com'
|
14
16
|
gem.files = `git ls-files`.split("\n")
|
15
17
|
gem.homepage = 'https://github.com/sferik/multi_xml'
|
data/spec/speed.rb
ADDED
@@ -0,0 +1,63 @@
|
|
1
|
+
#!/usr/bin/env ruby -wW1
|
2
|
+
|
3
|
+
$: << '.'
|
4
|
+
$: << '../lib'
|
5
|
+
|
6
|
+
if __FILE__ == $0
|
7
|
+
while (i = ARGV.index('-I'))
|
8
|
+
x,path = ARGV.slice!(i, 2)
|
9
|
+
$: << path
|
10
|
+
end
|
11
|
+
end
|
12
|
+
|
13
|
+
require 'optparse'
|
14
|
+
require 'stringio'
|
15
|
+
require 'multi_xml'
|
16
|
+
|
17
|
+
begin
|
18
|
+
require 'libxml'
|
19
|
+
rescue Exception => e
|
20
|
+
end
|
21
|
+
begin
|
22
|
+
require 'nokogiri'
|
23
|
+
rescue Exception => e
|
24
|
+
end
|
25
|
+
begin
|
26
|
+
require 'ox'
|
27
|
+
rescue Exception => e
|
28
|
+
end
|
29
|
+
|
30
|
+
$verbose = 0
|
31
|
+
$parsers = []
|
32
|
+
$iter = 10
|
33
|
+
|
34
|
+
opts = OptionParser.new
|
35
|
+
opts.on("-v", "increase verbosity") { $verbose += 1 }
|
36
|
+
opts.on("-p", "--parser [String]", String, "parser to test") { |p| $parsers = [p] }
|
37
|
+
opts.on("-i", "--iterations [Int]", Integer, "iterations") { |i| $iter = i }
|
38
|
+
opts.on("-h", "--help", "Show this display") { puts opts; Process.exit!(0) }
|
39
|
+
files = opts.parse(ARGV)
|
40
|
+
|
41
|
+
if $parsers.empty?
|
42
|
+
$parsers << 'libxml' if defined?(::LibXML)
|
43
|
+
$parsers << 'nokogiri' if defined?(::Nokogiri)
|
44
|
+
$parsers << 'ox' if defined?(::Ox)
|
45
|
+
end
|
46
|
+
|
47
|
+
files.each do |filename|
|
48
|
+
times = { }
|
49
|
+
xml = File.read(filename)
|
50
|
+
$parsers.each do |p|
|
51
|
+
MultiXml.parser = p
|
52
|
+
start = Time.now
|
53
|
+
$iter.times do |i|
|
54
|
+
io = StringIO.new(xml)
|
55
|
+
MultiXml.parse(io)
|
56
|
+
end
|
57
|
+
dt = Time.now - start
|
58
|
+
times[p] = Time.now - start
|
59
|
+
end
|
60
|
+
times.each do |p,t|
|
61
|
+
puts "%8s took %0.3f seconds to parse %s %d times." % [p, t, filename, $iter]
|
62
|
+
end
|
63
|
+
end
|
metadata
CHANGED
@@ -1,89 +1,151 @@
|
|
1
|
-
--- !ruby/object:Gem::Specification
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
2
|
name: multi_xml
|
3
|
-
version: !ruby/object:Gem::Version
|
4
|
-
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
hash: 13
|
5
5
|
prerelease:
|
6
|
+
segments:
|
7
|
+
- 0
|
8
|
+
- 4
|
9
|
+
- 1
|
10
|
+
version: 0.4.1
|
6
11
|
platform: ruby
|
7
|
-
authors:
|
12
|
+
authors:
|
8
13
|
- Erik Michaels-Ober
|
9
14
|
autorequire:
|
10
15
|
bindir: bin
|
11
16
|
cert_chain: []
|
12
|
-
|
13
|
-
|
14
|
-
|
17
|
+
|
18
|
+
date: 2011-09-26 00:00:00 Z
|
19
|
+
dependencies:
|
20
|
+
- !ruby/object:Gem::Dependency
|
21
|
+
name: libxml-ruby
|
22
|
+
prerelease: false
|
23
|
+
requirement: &id001 !ruby/object:Gem::Requirement
|
24
|
+
none: false
|
25
|
+
requirements:
|
26
|
+
- - ~>
|
27
|
+
- !ruby/object:Gem::Version
|
28
|
+
hash: 3
|
29
|
+
segments:
|
30
|
+
- 2
|
31
|
+
- 0
|
32
|
+
version: "2.0"
|
33
|
+
type: :development
|
34
|
+
version_requirements: *id001
|
35
|
+
- !ruby/object:Gem::Dependency
|
15
36
|
name: nokogiri
|
16
|
-
|
37
|
+
prerelease: false
|
38
|
+
requirement: &id002 !ruby/object:Gem::Requirement
|
17
39
|
none: false
|
18
|
-
requirements:
|
40
|
+
requirements:
|
19
41
|
- - ~>
|
20
|
-
- !ruby/object:Gem::Version
|
21
|
-
|
42
|
+
- !ruby/object:Gem::Version
|
43
|
+
hash: 7
|
44
|
+
segments:
|
45
|
+
- 1
|
46
|
+
- 4
|
47
|
+
version: "1.4"
|
22
48
|
type: :development
|
49
|
+
version_requirements: *id002
|
50
|
+
- !ruby/object:Gem::Dependency
|
51
|
+
name: ox
|
23
52
|
prerelease: false
|
24
|
-
|
25
|
-
- !ruby/object:Gem::Dependency
|
26
|
-
name: rake
|
27
|
-
requirement: &70174632547160 !ruby/object:Gem::Requirement
|
53
|
+
requirement: &id003 !ruby/object:Gem::Requirement
|
28
54
|
none: false
|
29
|
-
requirements:
|
55
|
+
requirements:
|
30
56
|
- - ~>
|
31
|
-
- !ruby/object:Gem::Version
|
32
|
-
|
57
|
+
- !ruby/object:Gem::Version
|
58
|
+
hash: 9
|
59
|
+
segments:
|
60
|
+
- 1
|
61
|
+
- 3
|
62
|
+
version: "1.3"
|
33
63
|
type: :development
|
64
|
+
version_requirements: *id003
|
65
|
+
- !ruby/object:Gem::Dependency
|
66
|
+
name: rake
|
34
67
|
prerelease: false
|
35
|
-
|
36
|
-
- !ruby/object:Gem::Dependency
|
37
|
-
name: rdiscount
|
38
|
-
requirement: &70174632529880 !ruby/object:Gem::Requirement
|
68
|
+
requirement: &id004 !ruby/object:Gem::Requirement
|
39
69
|
none: false
|
40
|
-
requirements:
|
70
|
+
requirements:
|
41
71
|
- - ~>
|
42
|
-
- !ruby/object:Gem::Version
|
43
|
-
|
72
|
+
- !ruby/object:Gem::Version
|
73
|
+
hash: 25
|
74
|
+
segments:
|
75
|
+
- 0
|
76
|
+
- 9
|
77
|
+
version: "0.9"
|
44
78
|
type: :development
|
79
|
+
version_requirements: *id004
|
80
|
+
- !ruby/object:Gem::Dependency
|
81
|
+
name: rdiscount
|
45
82
|
prerelease: false
|
46
|
-
|
47
|
-
- !ruby/object:Gem::Dependency
|
48
|
-
name: rspec
|
49
|
-
requirement: &70174632527760 !ruby/object:Gem::Requirement
|
83
|
+
requirement: &id005 !ruby/object:Gem::Requirement
|
50
84
|
none: false
|
51
|
-
requirements:
|
85
|
+
requirements:
|
52
86
|
- - ~>
|
53
|
-
- !ruby/object:Gem::Version
|
54
|
-
|
87
|
+
- !ruby/object:Gem::Version
|
88
|
+
hash: 3
|
89
|
+
segments:
|
90
|
+
- 1
|
91
|
+
- 6
|
92
|
+
version: "1.6"
|
55
93
|
type: :development
|
94
|
+
version_requirements: *id005
|
95
|
+
- !ruby/object:Gem::Dependency
|
96
|
+
name: rspec
|
56
97
|
prerelease: false
|
57
|
-
|
58
|
-
- !ruby/object:Gem::Dependency
|
59
|
-
name: simplecov
|
60
|
-
requirement: &70174632526060 !ruby/object:Gem::Requirement
|
98
|
+
requirement: &id006 !ruby/object:Gem::Requirement
|
61
99
|
none: false
|
62
|
-
requirements:
|
100
|
+
requirements:
|
63
101
|
- - ~>
|
64
|
-
- !ruby/object:Gem::Version
|
65
|
-
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
hash: 15
|
104
|
+
segments:
|
105
|
+
- 2
|
106
|
+
- 6
|
107
|
+
version: "2.6"
|
66
108
|
type: :development
|
109
|
+
version_requirements: *id006
|
110
|
+
- !ruby/object:Gem::Dependency
|
111
|
+
name: simplecov
|
67
112
|
prerelease: false
|
68
|
-
|
69
|
-
- !ruby/object:Gem::Dependency
|
70
|
-
name: yard
|
71
|
-
requirement: &70174632525380 !ruby/object:Gem::Requirement
|
113
|
+
requirement: &id007 !ruby/object:Gem::Requirement
|
72
114
|
none: false
|
73
|
-
requirements:
|
115
|
+
requirements:
|
74
116
|
- - ~>
|
75
|
-
- !ruby/object:Gem::Version
|
76
|
-
|
117
|
+
- !ruby/object:Gem::Version
|
118
|
+
hash: 3
|
119
|
+
segments:
|
120
|
+
- 0
|
121
|
+
- 4
|
122
|
+
version: "0.4"
|
77
123
|
type: :development
|
124
|
+
version_requirements: *id007
|
125
|
+
- !ruby/object:Gem::Dependency
|
126
|
+
name: yard
|
78
127
|
prerelease: false
|
79
|
-
|
80
|
-
|
81
|
-
|
128
|
+
requirement: &id008 !ruby/object:Gem::Requirement
|
129
|
+
none: false
|
130
|
+
requirements:
|
131
|
+
- - ~>
|
132
|
+
- !ruby/object:Gem::Version
|
133
|
+
hash: 5
|
134
|
+
segments:
|
135
|
+
- 0
|
136
|
+
- 7
|
137
|
+
version: "0.7"
|
138
|
+
type: :development
|
139
|
+
version_requirements: *id008
|
140
|
+
description: A gem to provide swappable XML backends utilizing LibXML, Nokogiri, Ox, or REXML.
|
82
141
|
email: sferik@gmail.com
|
83
142
|
executables: []
|
143
|
+
|
84
144
|
extensions: []
|
145
|
+
|
85
146
|
extra_rdoc_files: []
|
86
|
-
|
147
|
+
|
148
|
+
files:
|
87
149
|
- .gemtest
|
88
150
|
- .gitignore
|
89
151
|
- .rspec
|
@@ -104,31 +166,42 @@ files:
|
|
104
166
|
- spec/helper.rb
|
105
167
|
- spec/multi_xml_spec.rb
|
106
168
|
- spec/parser_shared_example.rb
|
169
|
+
- spec/speed.rb
|
107
170
|
homepage: https://github.com/sferik/multi_xml
|
108
171
|
licenses: []
|
172
|
+
|
109
173
|
post_install_message:
|
110
174
|
rdoc_options: []
|
111
|
-
|
175
|
+
|
176
|
+
require_paths:
|
112
177
|
- lib
|
113
|
-
required_ruby_version: !ruby/object:Gem::Requirement
|
178
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
114
179
|
none: false
|
115
|
-
requirements:
|
116
|
-
- -
|
117
|
-
- !ruby/object:Gem::Version
|
118
|
-
|
119
|
-
|
180
|
+
requirements:
|
181
|
+
- - ">="
|
182
|
+
- !ruby/object:Gem::Version
|
183
|
+
hash: 3
|
184
|
+
segments:
|
185
|
+
- 0
|
186
|
+
version: "0"
|
187
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
120
188
|
none: false
|
121
|
-
requirements:
|
122
|
-
- -
|
123
|
-
- !ruby/object:Gem::Version
|
124
|
-
|
189
|
+
requirements:
|
190
|
+
- - ">="
|
191
|
+
- !ruby/object:Gem::Version
|
192
|
+
hash: 3
|
193
|
+
segments:
|
194
|
+
- 0
|
195
|
+
version: "0"
|
125
196
|
requirements: []
|
197
|
+
|
126
198
|
rubyforge_project:
|
127
199
|
rubygems_version: 1.8.10
|
128
200
|
signing_key:
|
129
201
|
specification_version: 3
|
130
202
|
summary: A generic swappable back-end for XML parsing
|
131
|
-
test_files:
|
203
|
+
test_files:
|
132
204
|
- spec/helper.rb
|
133
205
|
- spec/multi_xml_spec.rb
|
134
206
|
- spec/parser_shared_example.rb
|
207
|
+
- spec/speed.rb
|