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
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
|
## -*- Ruby -*-
## XML::SimpleTreeBuilder
## 1998 by yoshidam
require 'xmlparser'
require 'xmltree'
include XML::SimpleTree
module XML
class SimpleTreeBuilder
## Contructor
## parser = XML::SimpleTreeBuilder.new(level)
## level: 0 -- ignore default events (defualt)
## 1 -- catch default events and create the Comment,
## the EntityReference, the XML declaration (as PI) and
## the non-DOM-compliant DocumentType nodes.
def initialize(level = 0)
@tree = nil
@parser = XMLParser.new
@level = level
if @level > 0
def @parser.default; end
end
end
## User redefinable name encoding converter
def nameConverter(str)
str
end
## User redefinable cdata encoding converter
def cdataConverter(str)
str
end
## Parse
## doctree = parser.parse(xml, trim)
## xml: string of XML contents
## trim: flag of extra-whitespace triming.
## This was not good idea.
## Use tree.documentElement.normalize; tree.trim
def parse(xml, trim = false)
tree = Document.new
current = tree
inDocDecl = 0
decl = ""
inDecl = 0
idRest = 0
docType = nil
extID = nil
cdata_f = 0
@parser.parse(xml) do |type, name, data|
case type
when XMLParser::START_ELEM
attr = {}
data.each do |key, value|
attr[nameConverter(key)] = cdataConverter(value)
end
elem = Element.new(nameConverter(name), attr)
current.appendChild(elem)
current = elem
when XMLParser::END_ELEM
current = current.parentNode
when XMLParser::CDATA
if data == ''
if @level > 0
cdata_f = 1
@parser.defaultCurrent
end
next
end
## next if trim && data =~ /^\s*$/
if cdata_f == 2
cdata = CDATASection.new(cdataConverter(data))
else
cdata = Text.new(cdataConverter(data))
end
current.appendChild(cdata)
when XMLParser::PI
pi = ProcessingInstruction.new(nameConverter(name),
cdataConverter(data))
## PI data should not be converted
current.appendChild(pi)
when XMLParser::DEFAULT
if cdata_f == 1
if data == '<![CDATA['
cdata_f = 2
elsif data == ']]>'
cdata_f = 0
else
print "Unexpected default event\n"
cdata_f = 0
end
next
end
## Large comment may crash regexp of Ruby
## if data =~ /^<!--([\s\S]*)-->$/
## comment = Comment.new(cdataConverter($1))
if data =~ /^<!--/ && data =~ /-->$/ && data.length >= 7
comment = Comment.new(cdataConverter(data[4..-4]))
## Comment should not be converted
current.appendChild(comment)
elsif data =~ /^\&(.+);$/
eref = EntityReference.new(nameConverter($1))
current.appendChild(eref)
elsif data =~ /^<\?xml\s*([\s\S]*)\?>$/
pi = ProcessingInstruction.new("xml",
cdataConverter($1))
## PI data should not be converted
current.appendChild(pi)
elsif inDocDecl == 0 && data =~ /^<\!DOCTYPE$/
inDocDecl = 1
inDecl = 0
idRest = 0
docType = nil
extID = nil
elsif inDocDecl == 1
if data == "["
inDocDecl = 2
elsif data == ">"
if !extID.nil?
current.nodeValue = extID
end
inDocDecl = 0
current = current.parentNode
elsif data == "SYSTEM"
idRest = 1
extID = data
elsif data == "PUBLIC"
idRest = 2
extID = data
elsif data !~ /^\s+$/
if idRest > 0
## SysID or PubID
extID <<= " " + data
idRest -= 1
else
## Root Element Type
docType = data
doctype = DocumentType.new(nameConverter(docType))
current.appendChild(doctype)
current = doctype
end
end
elsif inDocDecl == 2
if inDecl == 0
if data == "]"
inDocDecl = 1
elsif data =~ /^<\!/
decl = data
inDecl = 1
elsif data =~ /^%(.+);$/
## PERef
cdata = Text.new(nameConverter(data))
current.appendChild(cdata)
else
## WHITESPCAE
end
else ## inDecl == 1
if data == ">"
decl <<= data
inDecl = 0
## Markup Decl
cdata = Text.new(cdataConverter(decl))
## Markup decl should not be converted
current.appendChild(cdata)
elsif data =~ /^\s+$/
## WHITESPACE
decl << " "
else
decl << data
end
end
else
## maybe WHITESPACE
## next if tri m&& data =~ /^\s*$/
cdata = Text.new(cdataConverter(data))
current.appendChild(cdata)
end
end
end
tree
end
def line
@parser.line
end
def column
@parser.column
end
def byteIndex
@parser.byteIndex
end
end
module DOM
Builder = SimpleTreeBuilder
end
end
|
