rexml 3.1.7.3
Sign up to get free protection for your applications and to get access to all the features.
Potentially problematic release.
This version of rexml might be problematic. Click here for more details.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/.travis.yml +10 -0
- data/Gemfile +6 -0
- data/LICENSE.txt +22 -0
- data/README.md +60 -0
- data/Rakefile +10 -0
- data/bin/console +14 -0
- data/bin/setup +8 -0
- data/lib/rexml/attlistdecl.rb +63 -0
- data/lib/rexml/attribute.rb +192 -0
- data/lib/rexml/cdata.rb +68 -0
- data/lib/rexml/child.rb +97 -0
- data/lib/rexml/comment.rb +80 -0
- data/lib/rexml/doctype.rb +270 -0
- data/lib/rexml/document.rb +291 -0
- data/lib/rexml/dtd/attlistdecl.rb +11 -0
- data/lib/rexml/dtd/dtd.rb +47 -0
- data/lib/rexml/dtd/elementdecl.rb +18 -0
- data/lib/rexml/dtd/entitydecl.rb +57 -0
- data/lib/rexml/dtd/notationdecl.rb +40 -0
- data/lib/rexml/element.rb +1267 -0
- data/lib/rexml/encoding.rb +51 -0
- data/lib/rexml/entity.rb +171 -0
- data/lib/rexml/formatters/default.rb +112 -0
- data/lib/rexml/formatters/pretty.rb +142 -0
- data/lib/rexml/formatters/transitive.rb +58 -0
- data/lib/rexml/functions.rb +447 -0
- data/lib/rexml/instruction.rb +71 -0
- data/lib/rexml/light/node.rb +196 -0
- data/lib/rexml/namespace.rb +48 -0
- data/lib/rexml/node.rb +76 -0
- data/lib/rexml/output.rb +30 -0
- data/lib/rexml/parent.rb +166 -0
- data/lib/rexml/parseexception.rb +52 -0
- data/lib/rexml/parsers/baseparser.rb +586 -0
- data/lib/rexml/parsers/lightparser.rb +59 -0
- data/lib/rexml/parsers/pullparser.rb +197 -0
- data/lib/rexml/parsers/sax2parser.rb +273 -0
- data/lib/rexml/parsers/streamparser.rb +61 -0
- data/lib/rexml/parsers/treeparser.rb +101 -0
- data/lib/rexml/parsers/ultralightparser.rb +57 -0
- data/lib/rexml/parsers/xpathparser.rb +675 -0
- data/lib/rexml/quickpath.rb +266 -0
- data/lib/rexml/rexml.rb +32 -0
- data/lib/rexml/sax2listener.rb +98 -0
- data/lib/rexml/security.rb +28 -0
- data/lib/rexml/source.rb +298 -0
- data/lib/rexml/streamlistener.rb +93 -0
- data/lib/rexml/syncenumerator.rb +33 -0
- data/lib/rexml/text.rb +424 -0
- data/lib/rexml/undefinednamespaceexception.rb +9 -0
- data/lib/rexml/validation/relaxng.rb +539 -0
- data/lib/rexml/validation/validation.rb +144 -0
- data/lib/rexml/validation/validationexception.rb +10 -0
- data/lib/rexml/xmldecl.rb +116 -0
- data/lib/rexml/xmltokens.rb +85 -0
- data/lib/rexml/xpath.rb +81 -0
- data/lib/rexml/xpath_parser.rb +934 -0
- data/rexml.gemspec +42 -0
- metadata +131 -0
@@ -0,0 +1,51 @@
|
|
1
|
+
# coding: US-ASCII
|
2
|
+
# frozen_string_literal: false
|
3
|
+
module REXML
|
4
|
+
module Encoding
|
5
|
+
# ID ---> Encoding name
|
6
|
+
attr_reader :encoding
|
7
|
+
def encoding=(encoding)
|
8
|
+
encoding = encoding.name if encoding.is_a?(Encoding)
|
9
|
+
if encoding.is_a?(String)
|
10
|
+
original_encoding = encoding
|
11
|
+
encoding = find_encoding(encoding)
|
12
|
+
unless encoding
|
13
|
+
raise ArgumentError, "Bad encoding name #{original_encoding}"
|
14
|
+
end
|
15
|
+
end
|
16
|
+
return false if defined?(@encoding) and encoding == @encoding
|
17
|
+
if encoding
|
18
|
+
@encoding = encoding.upcase
|
19
|
+
else
|
20
|
+
@encoding = 'UTF-8'
|
21
|
+
end
|
22
|
+
true
|
23
|
+
end
|
24
|
+
|
25
|
+
def encode(string)
|
26
|
+
string.encode(@encoding)
|
27
|
+
end
|
28
|
+
|
29
|
+
def decode(string)
|
30
|
+
string.encode(::Encoding::UTF_8, @encoding)
|
31
|
+
end
|
32
|
+
|
33
|
+
private
|
34
|
+
def find_encoding(name)
|
35
|
+
case name
|
36
|
+
when /\Ashift-jis\z/i
|
37
|
+
return "SHIFT_JIS"
|
38
|
+
when /\ACP-(\d+)\z/
|
39
|
+
name = "CP#{$1}"
|
40
|
+
when /\AUTF-8\z/i
|
41
|
+
return name
|
42
|
+
end
|
43
|
+
begin
|
44
|
+
::Encoding::Converter.search_convpath(name, 'UTF-8')
|
45
|
+
rescue ::Encoding::ConverterNotFoundError
|
46
|
+
return nil
|
47
|
+
end
|
48
|
+
name
|
49
|
+
end
|
50
|
+
end
|
51
|
+
end
|
data/lib/rexml/entity.rb
ADDED
@@ -0,0 +1,171 @@
|
|
1
|
+
# frozen_string_literal: false
|
2
|
+
require_relative 'child'
|
3
|
+
require_relative 'source'
|
4
|
+
require_relative 'xmltokens'
|
5
|
+
|
6
|
+
module REXML
|
7
|
+
class Entity < Child
|
8
|
+
include XMLTokens
|
9
|
+
PUBIDCHAR = "\x20\x0D\x0Aa-zA-Z0-9\\-()+,./:=?;!*@$_%#"
|
10
|
+
SYSTEMLITERAL = %Q{((?:"[^"]*")|(?:'[^']*'))}
|
11
|
+
PUBIDLITERAL = %Q{("[#{PUBIDCHAR}']*"|'[#{PUBIDCHAR}]*')}
|
12
|
+
EXTERNALID = "(?:(?:(SYSTEM)\\s+#{SYSTEMLITERAL})|(?:(PUBLIC)\\s+#{PUBIDLITERAL}\\s+#{SYSTEMLITERAL}))"
|
13
|
+
NDATADECL = "\\s+NDATA\\s+#{NAME}"
|
14
|
+
PEREFERENCE = "%#{NAME};"
|
15
|
+
ENTITYVALUE = %Q{((?:"(?:[^%&"]|#{PEREFERENCE}|#{REFERENCE})*")|(?:'([^%&']|#{PEREFERENCE}|#{REFERENCE})*'))}
|
16
|
+
PEDEF = "(?:#{ENTITYVALUE}|#{EXTERNALID})"
|
17
|
+
ENTITYDEF = "(?:#{ENTITYVALUE}|(?:#{EXTERNALID}(#{NDATADECL})?))"
|
18
|
+
PEDECL = "<!ENTITY\\s+(%)\\s+#{NAME}\\s+#{PEDEF}\\s*>"
|
19
|
+
GEDECL = "<!ENTITY\\s+#{NAME}\\s+#{ENTITYDEF}\\s*>"
|
20
|
+
ENTITYDECL = /\s*(?:#{GEDECL})|(?:#{PEDECL})/um
|
21
|
+
|
22
|
+
attr_reader :name, :external, :ref, :ndata, :pubid
|
23
|
+
|
24
|
+
# Create a new entity. Simple entities can be constructed by passing a
|
25
|
+
# name, value to the constructor; this creates a generic, plain entity
|
26
|
+
# reference. For anything more complicated, you have to pass a Source to
|
27
|
+
# the constructor with the entity definition, or use the accessor methods.
|
28
|
+
# +WARNING+: There is no validation of entity state except when the entity
|
29
|
+
# is read from a stream. If you start poking around with the accessors,
|
30
|
+
# you can easily create a non-conformant Entity.
|
31
|
+
#
|
32
|
+
# e = Entity.new( 'amp', '&' )
|
33
|
+
def initialize stream, value=nil, parent=nil, reference=false
|
34
|
+
super(parent)
|
35
|
+
@ndata = @pubid = @value = @external = nil
|
36
|
+
if stream.kind_of? Array
|
37
|
+
@name = stream[1]
|
38
|
+
if stream[-1] == '%'
|
39
|
+
@reference = true
|
40
|
+
stream.pop
|
41
|
+
else
|
42
|
+
@reference = false
|
43
|
+
end
|
44
|
+
if stream[2] =~ /SYSTEM|PUBLIC/
|
45
|
+
@external = stream[2]
|
46
|
+
if @external == 'SYSTEM'
|
47
|
+
@ref = stream[3]
|
48
|
+
@ndata = stream[4] if stream.size == 5
|
49
|
+
else
|
50
|
+
@pubid = stream[3]
|
51
|
+
@ref = stream[4]
|
52
|
+
end
|
53
|
+
else
|
54
|
+
@value = stream[2]
|
55
|
+
end
|
56
|
+
else
|
57
|
+
@reference = reference
|
58
|
+
@external = nil
|
59
|
+
@name = stream
|
60
|
+
@value = value
|
61
|
+
end
|
62
|
+
end
|
63
|
+
|
64
|
+
# Evaluates whether the given string matches an entity definition,
|
65
|
+
# returning true if so, and false otherwise.
|
66
|
+
def Entity::matches? string
|
67
|
+
(ENTITYDECL =~ string) == 0
|
68
|
+
end
|
69
|
+
|
70
|
+
# Evaluates to the unnormalized value of this entity; that is, replacing
|
71
|
+
# all entities -- both %ent; and &ent; entities. This differs from
|
72
|
+
# +value()+ in that +value+ only replaces %ent; entities.
|
73
|
+
def unnormalized
|
74
|
+
document.record_entity_expansion unless document.nil?
|
75
|
+
v = value()
|
76
|
+
return nil if v.nil?
|
77
|
+
@unnormalized = Text::unnormalize(v, parent)
|
78
|
+
@unnormalized
|
79
|
+
end
|
80
|
+
|
81
|
+
#once :unnormalized
|
82
|
+
|
83
|
+
# Returns the value of this entity unprocessed -- raw. This is the
|
84
|
+
# normalized value; that is, with all %ent; and &ent; entities intact
|
85
|
+
def normalized
|
86
|
+
@value
|
87
|
+
end
|
88
|
+
|
89
|
+
# Write out a fully formed, correct entity definition (assuming the Entity
|
90
|
+
# object itself is valid.)
|
91
|
+
#
|
92
|
+
# out::
|
93
|
+
# An object implementing <TT><<<TT> to which the entity will be
|
94
|
+
# output
|
95
|
+
# indent::
|
96
|
+
# *DEPRECATED* and ignored
|
97
|
+
def write out, indent=-1
|
98
|
+
out << '<!ENTITY '
|
99
|
+
out << '% ' if @reference
|
100
|
+
out << @name
|
101
|
+
out << ' '
|
102
|
+
if @external
|
103
|
+
out << @external << ' '
|
104
|
+
if @pubid
|
105
|
+
q = @pubid.include?('"')?"'":'"'
|
106
|
+
out << q << @pubid << q << ' '
|
107
|
+
end
|
108
|
+
q = @ref.include?('"')?"'":'"'
|
109
|
+
out << q << @ref << q
|
110
|
+
out << ' NDATA ' << @ndata if @ndata
|
111
|
+
else
|
112
|
+
q = @value.include?('"')?"'":'"'
|
113
|
+
out << q << @value << q
|
114
|
+
end
|
115
|
+
out << '>'
|
116
|
+
end
|
117
|
+
|
118
|
+
# Returns this entity as a string. See write().
|
119
|
+
def to_s
|
120
|
+
rv = ''
|
121
|
+
write rv
|
122
|
+
rv
|
123
|
+
end
|
124
|
+
|
125
|
+
PEREFERENCE_RE = /#{PEREFERENCE}/um
|
126
|
+
# Returns the value of this entity. At the moment, only internal entities
|
127
|
+
# are processed. If the value contains internal references (IE,
|
128
|
+
# %blah;), those are replaced with their values. IE, if the doctype
|
129
|
+
# contains:
|
130
|
+
# <!ENTITY % foo "bar">
|
131
|
+
# <!ENTITY yada "nanoo %foo; nanoo>
|
132
|
+
# then:
|
133
|
+
# doctype.entity('yada').value #-> "nanoo bar nanoo"
|
134
|
+
def value
|
135
|
+
if @value
|
136
|
+
matches = @value.scan(PEREFERENCE_RE)
|
137
|
+
rv = @value.clone
|
138
|
+
if @parent
|
139
|
+
sum = 0
|
140
|
+
matches.each do |entity_reference|
|
141
|
+
entity_value = @parent.entity( entity_reference[0] )
|
142
|
+
if sum + entity_value.bytesize > Security.entity_expansion_text_limit
|
143
|
+
raise "entity expansion has grown too large"
|
144
|
+
else
|
145
|
+
sum += entity_value.bytesize
|
146
|
+
end
|
147
|
+
rv.gsub!( /%#{entity_reference.join};/um, entity_value )
|
148
|
+
end
|
149
|
+
end
|
150
|
+
return rv
|
151
|
+
end
|
152
|
+
nil
|
153
|
+
end
|
154
|
+
end
|
155
|
+
|
156
|
+
# This is a set of entity constants -- the ones defined in the XML
|
157
|
+
# specification. These are +gt+, +lt+, +amp+, +quot+ and +apos+.
|
158
|
+
# CAUTION: these entities does not have parent and document
|
159
|
+
module EntityConst
|
160
|
+
# +>+
|
161
|
+
GT = Entity.new( 'gt', '>' )
|
162
|
+
# +<+
|
163
|
+
LT = Entity.new( 'lt', '<' )
|
164
|
+
# +&+
|
165
|
+
AMP = Entity.new( 'amp', '&' )
|
166
|
+
# +"+
|
167
|
+
QUOT = Entity.new( 'quot', '"' )
|
168
|
+
# +'+
|
169
|
+
APOS = Entity.new( 'apos', "'" )
|
170
|
+
end
|
171
|
+
end
|
@@ -0,0 +1,112 @@
|
|
1
|
+
# frozen_string_literal: false
|
2
|
+
module REXML
|
3
|
+
module Formatters
|
4
|
+
class Default
|
5
|
+
# Prints out the XML document with no formatting -- except if ie_hack is
|
6
|
+
# set.
|
7
|
+
#
|
8
|
+
# ie_hack::
|
9
|
+
# If set to true, then inserts whitespace before the close of an empty
|
10
|
+
# tag, so that IE's bad XML parser doesn't choke.
|
11
|
+
def initialize( ie_hack=false )
|
12
|
+
@ie_hack = ie_hack
|
13
|
+
end
|
14
|
+
|
15
|
+
# Writes the node to some output.
|
16
|
+
#
|
17
|
+
# node::
|
18
|
+
# The node to write
|
19
|
+
# output::
|
20
|
+
# A class implementing <TT><<</TT>. Pass in an Output object to
|
21
|
+
# change the output encoding.
|
22
|
+
def write( node, output )
|
23
|
+
case node
|
24
|
+
|
25
|
+
when Document
|
26
|
+
if node.xml_decl.encoding != 'UTF-8' && !output.kind_of?(Output)
|
27
|
+
output = Output.new( output, node.xml_decl.encoding )
|
28
|
+
end
|
29
|
+
write_document( node, output )
|
30
|
+
|
31
|
+
when Element
|
32
|
+
write_element( node, output )
|
33
|
+
|
34
|
+
when Declaration, ElementDecl, NotationDecl, ExternalEntity, Entity,
|
35
|
+
Attribute, AttlistDecl
|
36
|
+
node.write( output,-1 )
|
37
|
+
|
38
|
+
when Instruction
|
39
|
+
write_instruction( node, output )
|
40
|
+
|
41
|
+
when DocType, XMLDecl
|
42
|
+
node.write( output )
|
43
|
+
|
44
|
+
when Comment
|
45
|
+
write_comment( node, output )
|
46
|
+
|
47
|
+
when CData
|
48
|
+
write_cdata( node, output )
|
49
|
+
|
50
|
+
when Text
|
51
|
+
write_text( node, output )
|
52
|
+
|
53
|
+
else
|
54
|
+
raise Exception.new("XML FORMATTING ERROR")
|
55
|
+
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
59
|
+
protected
|
60
|
+
def write_document( node, output )
|
61
|
+
node.children.each { |child| write( child, output ) }
|
62
|
+
end
|
63
|
+
|
64
|
+
def write_element( node, output )
|
65
|
+
output << "<#{node.expanded_name}"
|
66
|
+
|
67
|
+
node.attributes.to_a.map { |a|
|
68
|
+
Hash === a ? a.values : a
|
69
|
+
}.flatten.sort_by {|attr| attr.name || '' }.each do |attr|
|
70
|
+
output << " "
|
71
|
+
attr.write( output )
|
72
|
+
end unless node.attributes.empty?
|
73
|
+
|
74
|
+
if node.children.empty?
|
75
|
+
output << " " if @ie_hack
|
76
|
+
output << "/"
|
77
|
+
else
|
78
|
+
output << ">"
|
79
|
+
node.children.each { |child|
|
80
|
+
write( child, output )
|
81
|
+
}
|
82
|
+
output << "</#{node.expanded_name}"
|
83
|
+
end
|
84
|
+
output << ">"
|
85
|
+
end
|
86
|
+
|
87
|
+
def write_text( node, output )
|
88
|
+
output << node.to_s()
|
89
|
+
end
|
90
|
+
|
91
|
+
def write_comment( node, output )
|
92
|
+
output << Comment::START
|
93
|
+
output << node.to_s
|
94
|
+
output << Comment::STOP
|
95
|
+
end
|
96
|
+
|
97
|
+
def write_cdata( node, output )
|
98
|
+
output << CData::START
|
99
|
+
output << node.to_s
|
100
|
+
output << CData::STOP
|
101
|
+
end
|
102
|
+
|
103
|
+
def write_instruction( node, output )
|
104
|
+
output << Instruction::START.sub(/\\/u, '')
|
105
|
+
output << (node.target || '')
|
106
|
+
output << ' '
|
107
|
+
output << (node.content || '')
|
108
|
+
output << Instruction::STOP.sub(/\\/u, '')
|
109
|
+
end
|
110
|
+
end
|
111
|
+
end
|
112
|
+
end
|
@@ -0,0 +1,142 @@
|
|
1
|
+
# frozen_string_literal: false
|
2
|
+
require_relative 'default'
|
3
|
+
|
4
|
+
module REXML
|
5
|
+
module Formatters
|
6
|
+
# Pretty-prints an XML document. This destroys whitespace in text nodes
|
7
|
+
# and will insert carriage returns and indentations.
|
8
|
+
#
|
9
|
+
# TODO: Add an option to print attributes on new lines
|
10
|
+
class Pretty < Default
|
11
|
+
|
12
|
+
# If compact is set to true, then the formatter will attempt to use as
|
13
|
+
# little space as possible
|
14
|
+
attr_accessor :compact
|
15
|
+
# The width of a page. Used for formatting text
|
16
|
+
attr_accessor :width
|
17
|
+
|
18
|
+
# Create a new pretty printer.
|
19
|
+
#
|
20
|
+
# output::
|
21
|
+
# An object implementing '<<(String)', to which the output will be written.
|
22
|
+
# indentation::
|
23
|
+
# An integer greater than 0. The indentation of each level will be
|
24
|
+
# this number of spaces. If this is < 1, the behavior of this object
|
25
|
+
# is undefined. Defaults to 2.
|
26
|
+
# ie_hack::
|
27
|
+
# If true, the printer will insert whitespace before closing empty
|
28
|
+
# tags, thereby allowing Internet Explorer's XML parser to
|
29
|
+
# function. Defaults to false.
|
30
|
+
def initialize( indentation=2, ie_hack=false )
|
31
|
+
@indentation = indentation
|
32
|
+
@level = 0
|
33
|
+
@ie_hack = ie_hack
|
34
|
+
@width = 80
|
35
|
+
@compact = false
|
36
|
+
end
|
37
|
+
|
38
|
+
protected
|
39
|
+
def write_element(node, output)
|
40
|
+
output << ' '*@level
|
41
|
+
output << "<#{node.expanded_name}"
|
42
|
+
|
43
|
+
node.attributes.each_attribute do |attr|
|
44
|
+
output << " "
|
45
|
+
attr.write( output )
|
46
|
+
end unless node.attributes.empty?
|
47
|
+
|
48
|
+
if node.children.empty?
|
49
|
+
if @ie_hack
|
50
|
+
output << " "
|
51
|
+
end
|
52
|
+
output << "/"
|
53
|
+
else
|
54
|
+
output << ">"
|
55
|
+
# If compact and all children are text, and if the formatted output
|
56
|
+
# is less than the specified width, then try to print everything on
|
57
|
+
# one line
|
58
|
+
skip = false
|
59
|
+
if compact
|
60
|
+
if node.children.inject(true) {|s,c| s & c.kind_of?(Text)}
|
61
|
+
string = ""
|
62
|
+
old_level = @level
|
63
|
+
@level = 0
|
64
|
+
node.children.each { |child| write( child, string ) }
|
65
|
+
@level = old_level
|
66
|
+
if string.length < @width
|
67
|
+
output << string
|
68
|
+
skip = true
|
69
|
+
end
|
70
|
+
end
|
71
|
+
end
|
72
|
+
unless skip
|
73
|
+
output << "\n"
|
74
|
+
@level += @indentation
|
75
|
+
node.children.each { |child|
|
76
|
+
next if child.kind_of?(Text) and child.to_s.strip.length == 0
|
77
|
+
write( child, output )
|
78
|
+
output << "\n"
|
79
|
+
}
|
80
|
+
@level -= @indentation
|
81
|
+
output << ' '*@level
|
82
|
+
end
|
83
|
+
output << "</#{node.expanded_name}"
|
84
|
+
end
|
85
|
+
output << ">"
|
86
|
+
end
|
87
|
+
|
88
|
+
def write_text( node, output )
|
89
|
+
s = node.to_s()
|
90
|
+
s.gsub!(/\s/,' ')
|
91
|
+
s.squeeze!(" ")
|
92
|
+
s = wrap(s, @width - @level)
|
93
|
+
s = indent_text(s, @level, " ", true)
|
94
|
+
output << (' '*@level + s)
|
95
|
+
end
|
96
|
+
|
97
|
+
def write_comment( node, output)
|
98
|
+
output << ' ' * @level
|
99
|
+
super
|
100
|
+
end
|
101
|
+
|
102
|
+
def write_cdata( node, output)
|
103
|
+
output << ' ' * @level
|
104
|
+
super
|
105
|
+
end
|
106
|
+
|
107
|
+
def write_document( node, output )
|
108
|
+
# Ok, this is a bit odd. All XML documents have an XML declaration,
|
109
|
+
# but it may not write itself if the user didn't specifically add it,
|
110
|
+
# either through the API or in the input document. If it doesn't write
|
111
|
+
# itself, then we don't need a carriage return... which makes this
|
112
|
+
# logic more complex.
|
113
|
+
node.children.each { |child|
|
114
|
+
next if child == node.children[-1] and child.instance_of?(Text)
|
115
|
+
unless child == node.children[0] or child.instance_of?(Text) or
|
116
|
+
(child == node.children[1] and !node.children[0].writethis)
|
117
|
+
output << "\n"
|
118
|
+
end
|
119
|
+
write( child, output )
|
120
|
+
}
|
121
|
+
end
|
122
|
+
|
123
|
+
private
|
124
|
+
def indent_text(string, level=1, style="\t", indentfirstline=true)
|
125
|
+
return string if level < 0
|
126
|
+
string.gsub(/\n/, "\n#{style*level}")
|
127
|
+
end
|
128
|
+
|
129
|
+
def wrap(string, width)
|
130
|
+
parts = []
|
131
|
+
while string.length > width and place = string.rindex(' ', width)
|
132
|
+
parts << string[0...place]
|
133
|
+
string = string[place+1..-1]
|
134
|
+
end
|
135
|
+
parts << string
|
136
|
+
parts.join("\n")
|
137
|
+
end
|
138
|
+
|
139
|
+
end
|
140
|
+
end
|
141
|
+
end
|
142
|
+
|