1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
|
raise "JRuby is required to use the JDOM backend for XmlMini" unless RUBY_PLATFORM =~ /java/
require 'jruby'
include Java
import javax.xml.parsers.DocumentBuilder unless defined? DocumentBuilder
import javax.xml.parsers.DocumentBuilderFactory unless defined? DocumentBuilderFactory
import java.io.StringReader unless defined? StringReader
import org.xml.sax.InputSource unless defined? InputSource
import org.xml.sax.Attributes unless defined? Attributes
import org.w3c.dom.Node unless defined? Node
# = XmlMini JRuby JDOM implementation
module ActiveSupport
module XmlMini_JDOM #:nodoc:
extend self
CONTENT_KEY = '__content__'.freeze
NODE_TYPE_NAMES = %w{ATTRIBUTE_NODE CDATA_SECTION_NODE COMMENT_NODE DOCUMENT_FRAGMENT_NODE
DOCUMENT_NODE DOCUMENT_TYPE_NODE ELEMENT_NODE ENTITY_NODE ENTITY_REFERENCE_NODE NOTATION_NODE
PROCESSING_INSTRUCTION_NODE TEXT_NODE}
node_type_map = {}
NODE_TYPE_NAMES.each { |type| node_type_map[Node.send(type)] = type }
# Parse an XML Document string into a simple hash using Java's jdom.
# string::
# XML Document string to parse
def parse(string)
if string.blank?
{}
else
@dbf = DocumentBuilderFactory.new_instance
xml_string_reader = StringReader.new(string)
xml_input_source = InputSource.new(xml_string_reader)
doc = @dbf.new_document_builder.parse(xml_input_source)
merge_element!({}, doc.document_element)
end
end
private
# Convert an XML element and merge into the hash
#
# hash::
# Hash to merge the converted element into.
# element::
# XML element to merge into hash
def merge_element!(hash, element)
merge!(hash, element.tag_name, collapse(element))
end
# Actually converts an XML document element into a data structure.
#
# element::
# The document element to be collapsed.
def collapse(element)
hash = get_attributes(element)
child_nodes = element.child_nodes
if child_nodes.length > 0
for i in 0...child_nodes.length
child = child_nodes.item(i)
merge_element!(hash, child) unless child.node_type == Node.TEXT_NODE
end
merge_texts!(hash, element) unless empty_content?(element)
hash
else
merge_texts!(hash, element)
end
end
# Merge all the texts of an element into the hash
#
# hash::
# Hash to add the converted emement to.
# element::
# XML element whose texts are to me merged into the hash
def merge_texts!(hash, element)
text_children = texts(element)
if text_children.join.empty?
hash
else
# must use value to prevent double-escaping
merge!(hash, CONTENT_KEY, text_children.join)
end
end
# Adds a new key/value pair to an existing Hash. If the key to be added
# already exists and the existing value associated with key is not
# an Array, it will be wrapped in an Array. Then the new value is
# appended to that Array.
#
# hash::
# Hash to add key/value pair to.
# key::
# Key to be added.
# value::
# Value to be associated with key.
def merge!(hash, key, value)
if hash.has_key?(key)
if hash[key].instance_of?(Array)
hash[key] << value
else
hash[key] = [hash[key], value]
end
elsif value.instance_of?(Array)
hash[key] = [value]
else
hash[key] = value
end
hash
end
# Converts the attributes array of an XML element into a hash.
# Returns an empty Hash if node has no attributes.
#
# element::
# XML element to extract attributes from.
def get_attributes(element)
attribute_hash = {}
attributes = element.attributes
for i in 0...attributes.length
attribute_hash[attributes.item(i).name] = attributes.item(i).value
end
attribute_hash
end
# Determines if a document element has text content
#
# element::
# XML element to be checked.
def texts(element)
texts = []
child_nodes = element.child_nodes
for i in 0...child_nodes.length
item = child_nodes.item(i)
if item.node_type == Node.TEXT_NODE
texts << item.get_data
end
end
texts
end
# Determines if a document element has text content
#
# element::
# XML element to be checked.
def empty_content?(element)
text = ''
child_nodes = element.child_nodes
for i in 0...child_nodes.length
item = child_nodes.item(i)
if item.node_type == Node.TEXT_NODE
text << item.get_data.strip
end
end
text.strip.length == 0
end
end
end
|
