wannabeparser 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +2 -0
- data/Manifest +0 -0
- data/README.markdown +35 -0
- data/Rakefile +31 -0
- data/VERSION +1 -0
- data/examples/twitter.rb +22 -0
- data/examples/twitter.xml +3573 -0
- data/lib/wannabeparser.rb +79 -0
- metadata +71 -0
@@ -0,0 +1,79 @@
|
|
1
|
+
require 'rubygems'
|
2
|
+
require 'libxml'
|
3
|
+
|
4
|
+
module WannaBeParser
|
5
|
+
|
6
|
+
def self.included(base)
|
7
|
+
base.instance_variable_set("@elements", {})
|
8
|
+
base.instance_variable_set("@tag", {})
|
9
|
+
base.instance_variable_set("@process", {})
|
10
|
+
base.extend ClassMethods
|
11
|
+
end
|
12
|
+
|
13
|
+
module ClassMethods
|
14
|
+
def tag(tag)
|
15
|
+
@tag = tag
|
16
|
+
end
|
17
|
+
|
18
|
+
def element(o)
|
19
|
+
@elements.merge!(o)
|
20
|
+
end
|
21
|
+
|
22
|
+
def elements
|
23
|
+
@elements ||= {}
|
24
|
+
end
|
25
|
+
|
26
|
+
def process(func)
|
27
|
+
@process = func
|
28
|
+
end
|
29
|
+
|
30
|
+
def parse(filepath)
|
31
|
+
@counter = 0
|
32
|
+
@flow = LibXML::XML::Reader.document(document(filepath))
|
33
|
+
|
34
|
+
raise 'I/O error or no such file' if @flow.nil?
|
35
|
+
|
36
|
+
while @flow.read do
|
37
|
+
parse_tag(@flow.expand) if @flow.node_type == LibXML::XML::Reader::TYPE_ELEMENT && @flow.name == @tag
|
38
|
+
end
|
39
|
+
|
40
|
+
@counter
|
41
|
+
end
|
42
|
+
|
43
|
+
private
|
44
|
+
|
45
|
+
def parse_tag(node)
|
46
|
+
@basepath = node.path
|
47
|
+
@counter = @counter + 1
|
48
|
+
@process.call(parse_node(node))
|
49
|
+
end
|
50
|
+
|
51
|
+
def parse_node(node)
|
52
|
+
obj = {}
|
53
|
+
node.each_element { |n|
|
54
|
+
if (n.node_type == LibXML::XML::Reader::TYPE_ELEMENT)
|
55
|
+
key = @elements[n.name]||n.name
|
56
|
+
cLength, cFirst = n.children.length, n.first
|
57
|
+
value = cFirst ? cLength == 1 && cFirst.text? ? cFirst.content : parse_node(n) : nil
|
58
|
+
|
59
|
+
|
60
|
+
unless key.nil? or value.nil?
|
61
|
+
case obj[key]
|
62
|
+
when nil
|
63
|
+
obj[key] = value
|
64
|
+
when Array
|
65
|
+
obj[key].push(value)
|
66
|
+
else
|
67
|
+
obj[key] = [ obj[key], value ]
|
68
|
+
end
|
69
|
+
end
|
70
|
+
end
|
71
|
+
}
|
72
|
+
obj
|
73
|
+
end
|
74
|
+
|
75
|
+
def document(filepath)
|
76
|
+
LibXML::XML::Document.file(filepath)
|
77
|
+
end
|
78
|
+
end
|
79
|
+
end
|
metadata
ADDED
@@ -0,0 +1,71 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: wannabeparser
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Pasha Puzikov
|
8
|
+
autorequire:
|
9
|
+
bindir: bin
|
10
|
+
cert_chain: []
|
11
|
+
|
12
|
+
date: 2009-11-21 00:00:00 +03:00
|
13
|
+
default_executable:
|
14
|
+
dependencies:
|
15
|
+
- !ruby/object:Gem::Dependency
|
16
|
+
name: libxml-ruby
|
17
|
+
type: :runtime
|
18
|
+
version_requirement:
|
19
|
+
version_requirements: !ruby/object:Gem::Requirement
|
20
|
+
requirements:
|
21
|
+
- - "="
|
22
|
+
- !ruby/object:Gem::Version
|
23
|
+
version: 1.1.3
|
24
|
+
version:
|
25
|
+
description: Library for parsing xml to ruby hashes by input, selecting only specified tag contents
|
26
|
+
email: heydiplo@gmail.com
|
27
|
+
executables: []
|
28
|
+
|
29
|
+
extensions: []
|
30
|
+
|
31
|
+
extra_rdoc_files:
|
32
|
+
- README.markdown
|
33
|
+
files:
|
34
|
+
- .gitignore
|
35
|
+
- Manifest
|
36
|
+
- Rakefile
|
37
|
+
- VERSION
|
38
|
+
- examples/twitter.rb
|
39
|
+
- examples/twitter.xml
|
40
|
+
- lib/wannabeparser.rb
|
41
|
+
- README.markdown
|
42
|
+
has_rdoc: true
|
43
|
+
homepage: http://github.com/heydiplo/wannabeparser
|
44
|
+
licenses: []
|
45
|
+
|
46
|
+
post_install_message:
|
47
|
+
rdoc_options:
|
48
|
+
- --charset=UTF-8
|
49
|
+
require_paths:
|
50
|
+
- lib
|
51
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
52
|
+
requirements:
|
53
|
+
- - ">="
|
54
|
+
- !ruby/object:Gem::Version
|
55
|
+
version: "0"
|
56
|
+
version:
|
57
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - ">="
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: "0"
|
62
|
+
version:
|
63
|
+
requirements: []
|
64
|
+
|
65
|
+
rubyforge_project:
|
66
|
+
rubygems_version: 1.3.5
|
67
|
+
signing_key:
|
68
|
+
specification_version: 3
|
69
|
+
summary: Library for input-based xml to hash parsing
|
70
|
+
test_files:
|
71
|
+
- examples/twitter.rb
|