rubysl-rexml 1.0.0 → 2.0.1
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/.travis.yml +3 -2
- data/lib/rexml/attlistdecl.rb +56 -56
- data/lib/rexml/attribute.rb +155 -149
- data/lib/rexml/cdata.rb +48 -48
- data/lib/rexml/child.rb +82 -82
- data/lib/rexml/comment.rb +59 -59
- data/lib/rexml/doctype.rb +22 -24
- data/lib/rexml/document.rb +185 -129
- data/lib/rexml/dtd/attlistdecl.rb +7 -7
- data/lib/rexml/dtd/dtd.rb +41 -41
- data/lib/rexml/dtd/elementdecl.rb +13 -13
- data/lib/rexml/dtd/entitydecl.rb +49 -49
- data/lib/rexml/dtd/notationdecl.rb +32 -32
- data/lib/rexml/element.rb +122 -107
- data/lib/rexml/encoding.rb +37 -58
- data/lib/rexml/entity.rb +144 -144
- data/lib/rexml/formatters/default.rb +6 -4
- data/lib/rexml/formatters/pretty.rb +11 -8
- data/lib/rexml/formatters/transitive.rb +4 -3
- data/lib/rexml/functions.rb +33 -21
- data/lib/rexml/instruction.rb +49 -49
- data/lib/rexml/light/node.rb +190 -191
- data/lib/rexml/namespace.rb +39 -39
- data/lib/rexml/node.rb +38 -38
- data/lib/rexml/output.rb +17 -12
- data/lib/rexml/parent.rb +26 -25
- data/lib/rexml/parseexception.rb +4 -4
- data/lib/rexml/parsers/baseparser.rb +90 -61
- data/lib/rexml/parsers/lightparser.rb +41 -43
- data/lib/rexml/parsers/pullparser.rb +1 -1
- data/lib/rexml/parsers/sax2parser.rb +233 -198
- data/lib/rexml/parsers/streamparser.rb +6 -2
- data/lib/rexml/parsers/treeparser.rb +9 -6
- data/lib/rexml/parsers/ultralightparser.rb +40 -40
- data/lib/rexml/parsers/xpathparser.rb +51 -52
- data/lib/rexml/quickpath.rb +247 -248
- data/lib/rexml/rexml.rb +9 -10
- data/lib/rexml/sax2listener.rb +92 -92
- data/lib/rexml/security.rb +27 -0
- data/lib/rexml/source.rb +95 -50
- data/lib/rexml/streamlistener.rb +90 -90
- data/lib/rexml/syncenumerator.rb +3 -4
- data/lib/rexml/text.rb +157 -76
- data/lib/rexml/validation/relaxng.rb +18 -18
- data/lib/rexml/validation/validation.rb +5 -5
- data/lib/rexml/xmldecl.rb +59 -63
- data/lib/rexml/xmltokens.rb +14 -14
- data/lib/rexml/xpath.rb +67 -53
- data/lib/rexml/xpath_parser.rb +49 -38
- data/lib/rubysl/rexml.rb +1 -0
- data/lib/rubysl/rexml/version.rb +1 -1
- data/rubysl-rexml.gemspec +3 -1
- metadata +19 -28
- data/lib/rexml/encodings/CP-1252.rb +0 -103
- data/lib/rexml/encodings/EUC-JP.rb +0 -35
- data/lib/rexml/encodings/ICONV.rb +0 -22
- data/lib/rexml/encodings/ISO-8859-1.rb +0 -7
- data/lib/rexml/encodings/ISO-8859-15.rb +0 -72
- data/lib/rexml/encodings/SHIFT-JIS.rb +0 -37
- data/lib/rexml/encodings/SHIFT_JIS.rb +0 -1
- data/lib/rexml/encodings/UNILE.rb +0 -34
- data/lib/rexml/encodings/US-ASCII.rb +0 -30
- data/lib/rexml/encodings/UTF-16.rb +0 -35
- data/lib/rexml/encodings/UTF-8.rb +0 -18
data/lib/rexml/document.rb
CHANGED
@@ -1,3 +1,4 @@
|
|
1
|
+
require "rexml/security"
|
1
2
|
require "rexml/element"
|
2
3
|
require "rexml/xmldecl"
|
3
4
|
require "rexml/source"
|
@@ -16,131 +17,138 @@ module REXML
|
|
16
17
|
# Document has a single child that can be accessed by root().
|
17
18
|
# Note that if you want to have an XML declaration written for a document
|
18
19
|
# you create, you must add one; REXML documents do not write a default
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
|
20
|
+
# declaration for you. See |DECLARATION| and |write|.
|
21
|
+
class Document < Element
|
22
|
+
# A convenient default XML declaration. If you want an XML declaration,
|
23
|
+
# the easiest way to add one is mydoc << Document::DECLARATION
|
23
24
|
# +DEPRECATED+
|
24
25
|
# Use: mydoc << XMLDecl.default
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
|
26
|
+
DECLARATION = XMLDecl.default
|
27
|
+
|
28
|
+
# Constructor
|
29
|
+
# @param source if supplied, must be a Document, String, or IO.
|
30
|
+
# Documents have their context and Element attributes cloned.
|
31
|
+
# Strings are expected to be valid XML documents. IOs are expected
|
32
|
+
# to be sources of valid XML documents.
|
33
|
+
# @param context if supplied, contains the context of the document;
|
34
|
+
# this should be a Hash.
|
35
|
+
def initialize( source = nil, context = {} )
|
35
36
|
@entity_expansion_count = 0
|
36
|
-
|
37
|
-
|
38
|
-
|
39
|
-
|
40
|
-
|
41
|
-
|
42
|
-
|
43
|
-
|
44
|
-
|
45
|
-
|
37
|
+
super()
|
38
|
+
@context = context
|
39
|
+
return if source.nil?
|
40
|
+
if source.kind_of? Document
|
41
|
+
@context = source.context
|
42
|
+
super source
|
43
|
+
else
|
44
|
+
build( source )
|
45
|
+
end
|
46
|
+
end
|
46
47
|
|
47
48
|
def node_type
|
48
49
|
:document
|
49
50
|
end
|
50
51
|
|
51
|
-
|
52
|
-
|
53
|
-
|
54
|
-
|
52
|
+
# Should be obvious
|
53
|
+
def clone
|
54
|
+
Document.new self
|
55
|
+
end
|
55
56
|
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
57
|
+
# According to the XML spec, a root node has no expanded name
|
58
|
+
def expanded_name
|
59
|
+
''
|
60
|
+
#d = doc_type
|
61
|
+
#d ? d.name : "UNDEFINED"
|
62
|
+
end
|
62
63
|
|
63
|
-
|
64
|
+
alias :name :expanded_name
|
64
65
|
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
66
|
+
# We override this, because XMLDecls and DocTypes must go at the start
|
67
|
+
# of the document
|
68
|
+
def add( child )
|
69
|
+
if child.kind_of? XMLDecl
|
70
|
+
if @children[0].kind_of? XMLDecl
|
71
|
+
@children[0] = child
|
72
|
+
else
|
73
|
+
@children.unshift child
|
74
|
+
end
|
70
75
|
child.parent = self
|
71
|
-
|
72
|
-
# Find first Element or DocType node and insert the decl right
|
76
|
+
elsif child.kind_of? DocType
|
77
|
+
# Find first Element or DocType node and insert the decl right
|
73
78
|
# before it. If there is no such node, just insert the child at the
|
74
79
|
# end. If there is a child and it is an DocType, then replace it.
|
75
|
-
insert_before_index =
|
76
|
-
@children.find { |x|
|
77
|
-
insert_before_index += 1
|
80
|
+
insert_before_index = @children.find_index { |x|
|
78
81
|
x.kind_of?(Element) || x.kind_of?(DocType)
|
79
82
|
}
|
80
|
-
if
|
81
|
-
if @children[ insert_before_index ].kind_of DocType
|
83
|
+
if insert_before_index # Not null = not end of list
|
84
|
+
if @children[ insert_before_index ].kind_of? DocType
|
82
85
|
@children[ insert_before_index ] = child
|
83
86
|
else
|
84
|
-
@children[
|
87
|
+
@children[ insert_before_index-1, 0 ] = child
|
85
88
|
end
|
86
89
|
else # Insert at end of list
|
87
|
-
@children
|
90
|
+
@children << child
|
88
91
|
end
|
89
|
-
|
90
|
-
|
91
|
-
|
92
|
-
|
93
|
-
|
94
|
-
|
95
|
-
|
96
|
-
|
97
|
-
|
98
|
-
|
99
|
-
|
100
|
-
|
101
|
-
|
102
|
-
|
103
|
-
|
104
|
-
|
105
|
-
|
106
|
-
|
92
|
+
child.parent = self
|
93
|
+
else
|
94
|
+
rv = super
|
95
|
+
raise "attempted adding second root element to document" if @elements.size > 1
|
96
|
+
rv
|
97
|
+
end
|
98
|
+
end
|
99
|
+
alias :<< :add
|
100
|
+
|
101
|
+
def add_element(arg=nil, arg2=nil)
|
102
|
+
rv = super
|
103
|
+
raise "attempted adding second root element to document" if @elements.size > 1
|
104
|
+
rv
|
105
|
+
end
|
106
|
+
|
107
|
+
# @return the root Element of the document, or nil if this document
|
108
|
+
# has no children.
|
109
|
+
def root
|
107
110
|
elements[1]
|
108
111
|
#self
|
109
112
|
#@children.find { |item| item.kind_of? Element }
|
110
|
-
|
111
|
-
|
112
|
-
|
113
|
-
|
114
|
-
|
115
|
-
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
|
120
|
-
|
121
|
-
|
113
|
+
end
|
114
|
+
|
115
|
+
# @return the DocType child of the document, if one exists,
|
116
|
+
# and nil otherwise.
|
117
|
+
def doctype
|
118
|
+
@children.find { |item| item.kind_of? DocType }
|
119
|
+
end
|
120
|
+
|
121
|
+
# @return the XMLDecl of this document; if no XMLDecl has been
|
122
|
+
# set, the default declaration is returned.
|
123
|
+
def xml_decl
|
124
|
+
rv = @children[0]
|
122
125
|
return rv if rv.kind_of? XMLDecl
|
123
126
|
rv = @children.unshift(XMLDecl.default)[0]
|
124
|
-
|
125
|
-
|
126
|
-
|
127
|
-
|
128
|
-
|
129
|
-
|
130
|
-
|
131
|
-
|
132
|
-
|
133
|
-
|
134
|
-
|
135
|
-
|
136
|
-
|
137
|
-
|
138
|
-
|
139
|
-
|
140
|
-
|
141
|
-
|
142
|
-
|
127
|
+
end
|
128
|
+
|
129
|
+
# @return the XMLDecl version of this document as a String.
|
130
|
+
# If no XMLDecl has been set, returns the default version.
|
131
|
+
def version
|
132
|
+
xml_decl().version
|
133
|
+
end
|
134
|
+
|
135
|
+
# @return the XMLDecl encoding of this document as an
|
136
|
+
# Encoding object.
|
137
|
+
# If no XMLDecl has been set, returns the default encoding.
|
138
|
+
def encoding
|
139
|
+
xml_decl().encoding
|
140
|
+
end
|
141
|
+
|
142
|
+
# @return the XMLDecl standalone value of this document as a String.
|
143
|
+
# If no XMLDecl has been set, returns the default setting.
|
144
|
+
def stand_alone?
|
145
|
+
xml_decl().stand_alone?
|
146
|
+
end
|
143
147
|
|
148
|
+
# :call-seq:
|
149
|
+
# doc.write(output=$stdout, indent=-1, transtive=false, ie_hack=false, encoding=nil)
|
150
|
+
# doc.write(options={:output => $stdout, :indent => -1, :transtive => false, :ie_hack => false, :encoding => nil})
|
151
|
+
#
|
144
152
|
# Write the XML tree out, optionally with indent. This writes out the
|
145
153
|
# entire XML document, including XML declarations, doctype declarations,
|
146
154
|
# and processing instructions (if any are given).
|
@@ -151,41 +159,73 @@ module REXML
|
|
151
159
|
# specified, because it adds unnecessary bandwidth to applications such
|
152
160
|
# as XML-RPC.
|
153
161
|
#
|
162
|
+
# Accept Nth argument style and options Hash style as argument.
|
163
|
+
# The recommended style is options Hash style for one or more
|
164
|
+
# arguments case.
|
165
|
+
#
|
166
|
+
# _Examples_
|
167
|
+
# Document.new("<a><b/></a>").write
|
168
|
+
#
|
169
|
+
# output = ""
|
170
|
+
# Document.new("<a><b/></a>").write(output)
|
171
|
+
#
|
172
|
+
# output = ""
|
173
|
+
# Document.new("<a><b/></a>").write(:output => output, :indent => 2)
|
174
|
+
#
|
154
175
|
# See also the classes in the rexml/formatters package for the proper way
|
155
|
-
# to change the default formatting of XML output
|
176
|
+
# to change the default formatting of XML output.
|
156
177
|
#
|
157
178
|
# _Examples_
|
158
|
-
# Document.new("<a><b/></a>").serialize
|
159
179
|
#
|
160
|
-
#
|
161
|
-
# tr = Transitive.new
|
162
|
-
# Document.new("<a><b/></a>")
|
180
|
+
# output = ""
|
181
|
+
# tr = Transitive.new
|
182
|
+
# tr.write(Document.new("<a><b/></a>"), output)
|
163
183
|
#
|
164
184
|
# output::
|
165
|
-
#
|
185
|
+
# output an object which supports '<< string'; this is where the
|
166
186
|
# document will be written.
|
167
187
|
# indent::
|
168
188
|
# An integer. If -1, no indenting will be used; otherwise, the
|
169
189
|
# indentation will be twice this number of spaces, and children will be
|
170
|
-
# indented an additional amount. For a value of 3, every item will be
|
190
|
+
# indented an additional amount. For a value of 3, every item will be
|
171
191
|
# indented 3 more levels, or 6 more spaces (2 * 3). Defaults to -1
|
172
|
-
#
|
192
|
+
# transitive::
|
173
193
|
# If transitive is true and indent is >= 0, then the output will be
|
174
194
|
# pretty-printed in such a way that the added whitespace does not affect
|
175
195
|
# the absolute *value* of the document -- that is, it leaves the value
|
176
196
|
# and number of Text nodes in the document unchanged.
|
177
197
|
# ie_hack::
|
178
|
-
#
|
179
|
-
#
|
180
|
-
#
|
181
|
-
#
|
182
|
-
#
|
183
|
-
|
184
|
-
|
185
|
-
|
198
|
+
# This hack inserts a space before the /> on empty tags to address
|
199
|
+
# a limitation of Internet Explorer. Defaults to false
|
200
|
+
# encoding::
|
201
|
+
# Encoding name as String. Change output encoding to specified encoding
|
202
|
+
# instead of encoding in XML declaration.
|
203
|
+
# Defaults to nil. It means encoding in XML declaration is used.
|
204
|
+
def write(*arguments)
|
205
|
+
if arguments.size == 1 and arguments[0].class == Hash
|
206
|
+
options = arguments[0]
|
207
|
+
|
208
|
+
output = options[:output]
|
209
|
+
indent = options[:indent]
|
210
|
+
transitive = options[:transitive]
|
211
|
+
ie_hack = options[:ie_hack]
|
212
|
+
encoding = options[:encoding]
|
213
|
+
else
|
214
|
+
output, indent, transitive, ie_hack, encoding, = *arguments
|
215
|
+
end
|
216
|
+
|
217
|
+
output ||= $stdout
|
218
|
+
indent ||= -1
|
219
|
+
transitive = false if transitive.nil?
|
220
|
+
ie_hack = false if ie_hack.nil?
|
221
|
+
encoding ||= xml_decl.encoding
|
222
|
+
|
223
|
+
if encoding != 'UTF-8' && !output.kind_of?(Output)
|
224
|
+
output = Output.new( output, encoding )
|
186
225
|
end
|
187
226
|
formatter = if indent > -1
|
188
|
-
if
|
227
|
+
if transitive
|
228
|
+
require "rexml/formatters/transitive"
|
189
229
|
REXML::Formatters::Transitive.new( indent, ie_hack )
|
190
230
|
else
|
191
231
|
REXML::Formatters::Pretty.new( indent, ie_hack )
|
@@ -194,37 +234,53 @@ module REXML
|
|
194
234
|
REXML::Formatters::Default.new( ie_hack )
|
195
235
|
end
|
196
236
|
formatter.write( self, output )
|
197
|
-
|
237
|
+
end
|
198
238
|
|
199
|
-
|
200
|
-
def Document::parse_stream( source, listener )
|
201
|
-
Parsers::StreamParser.new( source, listener ).parse
|
202
|
-
end
|
203
239
|
|
204
|
-
|
240
|
+
def Document::parse_stream( source, listener )
|
241
|
+
Parsers::StreamParser.new( source, listener ).parse
|
242
|
+
end
|
205
243
|
|
206
244
|
# Set the entity expansion limit. By default the limit is set to 10000.
|
245
|
+
#
|
246
|
+
# Deprecated. Use REXML::Security.entity_expansion_limit= instead.
|
207
247
|
def Document::entity_expansion_limit=( val )
|
208
|
-
|
248
|
+
Security.entity_expansion_limit = val
|
209
249
|
end
|
210
250
|
|
211
251
|
# Get the entity expansion limit. By default the limit is set to 10000.
|
252
|
+
#
|
253
|
+
# Deprecated. Use REXML::Security.entity_expansion_limit= instead.
|
212
254
|
def Document::entity_expansion_limit
|
213
|
-
return
|
255
|
+
return Security.entity_expansion_limit
|
256
|
+
end
|
257
|
+
|
258
|
+
# Set the entity expansion limit. By default the limit is set to 10240.
|
259
|
+
#
|
260
|
+
# Deprecated. Use REXML::Security.entity_expansion_text_limit= instead.
|
261
|
+
def Document::entity_expansion_text_limit=( val )
|
262
|
+
Security.entity_expansion_text_limit = val
|
263
|
+
end
|
264
|
+
|
265
|
+
# Get the entity expansion limit. By default the limit is set to 10240.
|
266
|
+
#
|
267
|
+
# Deprecated. Use REXML::Security.entity_expansion_text_limit instead.
|
268
|
+
def Document::entity_expansion_text_limit
|
269
|
+
return Security.entity_expansion_text_limit
|
214
270
|
end
|
215
271
|
|
216
272
|
attr_reader :entity_expansion_count
|
217
|
-
|
273
|
+
|
218
274
|
def record_entity_expansion
|
219
275
|
@entity_expansion_count += 1
|
220
|
-
if @entity_expansion_count >
|
276
|
+
if @entity_expansion_count > Security.entity_expansion_limit
|
221
277
|
raise "number of entity expansions exceeded, processing aborted."
|
222
278
|
end
|
223
279
|
end
|
224
280
|
|
225
|
-
|
226
|
-
|
281
|
+
private
|
282
|
+
def build( source )
|
227
283
|
Parsers::TreeParser.new( source, self ).parse
|
228
|
-
|
229
|
-
|
284
|
+
end
|
285
|
+
end
|
230
286
|
end
|
@@ -1,10 +1,10 @@
|
|
1
1
|
require "rexml/child"
|
2
2
|
module REXML
|
3
|
-
|
4
|
-
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
|
3
|
+
module DTD
|
4
|
+
class AttlistDecl < Child
|
5
|
+
START = "<!ATTLIST"
|
6
|
+
START_RE = /^\s*#{START}/um
|
7
|
+
PATTERN_RE = /\s*(#{START}.*?>)/um
|
8
|
+
end
|
9
|
+
end
|
10
10
|
end
|
data/lib/rexml/dtd/dtd.rb
CHANGED
@@ -6,46 +6,46 @@ require "rexml/dtd/attlistdecl"
|
|
6
6
|
require "rexml/parent"
|
7
7
|
|
8
8
|
module REXML
|
9
|
-
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
|
16
|
-
|
17
|
-
|
18
|
-
|
9
|
+
module DTD
|
10
|
+
class Parser
|
11
|
+
def Parser.parse( input )
|
12
|
+
case input
|
13
|
+
when String
|
14
|
+
parse_helper input
|
15
|
+
when File
|
16
|
+
parse_helper input.read
|
17
|
+
end
|
18
|
+
end
|
19
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
|
-
|
20
|
+
# Takes a String and parses it out
|
21
|
+
def Parser.parse_helper( input )
|
22
|
+
contents = Parent.new
|
23
|
+
while input.size > 0
|
24
|
+
case input
|
25
|
+
when ElementDecl.PATTERN_RE
|
26
|
+
match = $&
|
27
|
+
source = $'
|
28
|
+
contents << ElementDecl.new( match )
|
29
|
+
when AttlistDecl.PATTERN_RE
|
30
|
+
matchdata = $~
|
31
|
+
source = $'
|
32
|
+
contents << AttlistDecl.new( matchdata )
|
33
|
+
when EntityDecl.PATTERN_RE
|
34
|
+
matchdata = $~
|
35
|
+
source = $'
|
36
|
+
contents << EntityDecl.new( matchdata )
|
37
|
+
when Comment.PATTERN_RE
|
38
|
+
matchdata = $~
|
39
|
+
source = $'
|
40
|
+
contents << Comment.new( matchdata )
|
41
|
+
when NotationDecl.PATTERN_RE
|
42
|
+
matchdata = $~
|
43
|
+
source = $'
|
44
|
+
contents << NotationDecl.new( matchdata )
|
45
|
+
end
|
46
|
+
end
|
47
|
+
contents
|
48
|
+
end
|
49
|
+
end
|
50
|
+
end
|
51
51
|
end
|