libxml-jruby 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data/History.txt +4 -0
- data/README.txt +50 -0
- data/Rakefile +19 -0
- data/VERSION +1 -0
- data/VERSION.yml +5 -0
- data/lib/libxml-jruby.rb +84 -0
- data/lib/libxml-jruby/xml.rb +1 -0
- data/lib/libxml-jruby/xml/attr.rb +46 -0
- data/lib/libxml-jruby/xml/attributes.rb +68 -0
- data/lib/libxml-jruby/xml/document.rb +52 -0
- data/lib/libxml-jruby/xml/dtd.rb +25 -0
- data/lib/libxml-jruby/xml/node.rb +285 -0
- data/lib/libxml-jruby/xml/ns.rb +19 -0
- data/lib/libxml-jruby/xml/parser.rb +121 -0
- data/lib/libxml-jruby/xml/xpath.rb +98 -0
- data/lib/libxml.rb +1 -0
- data/lib/xml.rb +13 -0
- data/lib/xml/libxml.rb +8 -0
- data/test/etc_doc_to_s.rb +19 -0
- data/test/ets_copy_bug.rb +21 -0
- data/test/ets_copy_bug3.rb +38 -0
- data/test/ets_doc_file.rb +15 -0
- data/test/ets_doc_to_s.rb +21 -0
- data/test/ets_gpx.rb +26 -0
- data/test/ets_node_gc.rb +21 -0
- data/test/ets_tsr.rb +9 -0
- data/test/model/default_validation_bug.rb +0 -0
- data/test/tc_attributes.rb +110 -0
- data/test/tc_deprecated_require.rb +13 -0
- data/test/tc_document.rb +97 -0
- data/test/tc_document_write.rb +139 -0
- data/test/tc_dtd.rb +70 -0
- data/test/tc_html_parser.rb +63 -0
- data/test/tc_node.rb +108 -0
- data/test/tc_node_attr.rb +176 -0
- data/test/tc_node_cdata.rb +51 -0
- data/test/tc_node_comment.rb +32 -0
- data/test/tc_node_copy.rb +40 -0
- data/test/tc_node_edit.rb +98 -0
- data/test/tc_node_set.rb +24 -0
- data/test/tc_node_set2.rb +37 -0
- data/test/tc_node_text.rb +17 -0
- data/test/tc_node_xlink.rb +28 -0
- data/test/tc_ns.rb +18 -0
- data/test/tc_parser.rb +308 -0
- data/test/tc_parser_context.rb +126 -0
- data/test/tc_properties.rb +37 -0
- data/test/tc_reader.rb +112 -0
- data/test/tc_relaxng.rb +39 -0
- data/test/tc_sax_parser.rb +113 -0
- data/test/tc_schema.rb +39 -0
- data/test/tc_traversal.rb +220 -0
- data/test/tc_well_formed.rb +11 -0
- data/test/tc_xinclude.rb +26 -0
- data/test/tc_xpath.rb +130 -0
- data/test/tc_xpath_context.rb +72 -0
- data/test/tc_xpointer.rb +78 -0
- data/test/test_libxml-jruby.rb +0 -0
- data/test/test_suite.rb +31 -0
- data/test/ts_working.rb +31 -0
- metadata +121 -0
@@ -0,0 +1,19 @@
|
|
1
|
+
module LibXMLJRuby
|
2
|
+
module XML
|
3
|
+
class NS
|
4
|
+
class << self
|
5
|
+
def from_java(java_obj)
|
6
|
+
|
7
|
+
end
|
8
|
+
end
|
9
|
+
|
10
|
+
def initialize(node, href, prefix)
|
11
|
+
@node, @href, @prefix = node, href, prefix
|
12
|
+
end
|
13
|
+
|
14
|
+
attr_reader :href, :prefix
|
15
|
+
def href?; !!href; end
|
16
|
+
def prefix?; !!prefix; end
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
@@ -0,0 +1,121 @@
|
|
1
|
+
class LibXMLJRuby::XML::Parser
|
2
|
+
class ParseError < RuntimeError; end
|
3
|
+
|
4
|
+
VERNUM = 0
|
5
|
+
VERSION = '0'
|
6
|
+
|
7
|
+
@default_tree_indent_string = ' '
|
8
|
+
@check_lib_versions = ''
|
9
|
+
@features = []
|
10
|
+
|
11
|
+
class << self
|
12
|
+
attr_accessor :debug_entities, :default_compression,
|
13
|
+
:default_keep_blanks, :default_line_numbers,
|
14
|
+
:default_substitute_entities,
|
15
|
+
:default_tree_indent_string,
|
16
|
+
:default_validity_checking, :default_warnings,
|
17
|
+
:features, :indent_tree_output,
|
18
|
+
:check_lib_versions
|
19
|
+
|
20
|
+
def register_error_handler(handler = nil, &block)
|
21
|
+
|
22
|
+
end
|
23
|
+
|
24
|
+
def file(filename)
|
25
|
+
p = new
|
26
|
+
p.filename = filename
|
27
|
+
p
|
28
|
+
end
|
29
|
+
|
30
|
+
def string(string)
|
31
|
+
p = new
|
32
|
+
p.string = string
|
33
|
+
p
|
34
|
+
end
|
35
|
+
|
36
|
+
def io(io)
|
37
|
+
p = new
|
38
|
+
p.io = io
|
39
|
+
p
|
40
|
+
end
|
41
|
+
end
|
42
|
+
|
43
|
+
def initialize
|
44
|
+
@source_type = nil
|
45
|
+
@parsed = false
|
46
|
+
end
|
47
|
+
|
48
|
+
attr_reader :string, :filename, :io
|
49
|
+
|
50
|
+
def string=(string = nil)
|
51
|
+
raise TypeError if string.nil?
|
52
|
+
@parsed = false
|
53
|
+
@source_type = String
|
54
|
+
@string = string
|
55
|
+
end
|
56
|
+
|
57
|
+
def filename=(filename)
|
58
|
+
@source_type = File
|
59
|
+
@filename = filename
|
60
|
+
end
|
61
|
+
|
62
|
+
def io=(io)
|
63
|
+
raise TypeError if StringIO === io
|
64
|
+
@io = io
|
65
|
+
self.string = @io.read
|
66
|
+
end
|
67
|
+
|
68
|
+
def parse
|
69
|
+
raise ParseError, "You cannot parse twice" if @parsed
|
70
|
+
raise ParseError, "No input specified, please specify an input" unless @source_type
|
71
|
+
doc = send("parse_#{@source_type.to_s.downcase}")
|
72
|
+
@parsed = true
|
73
|
+
doc
|
74
|
+
end
|
75
|
+
|
76
|
+
def document_builder_factory
|
77
|
+
@dbf ||= DocumentBuilderFactory.new_instance
|
78
|
+
end
|
79
|
+
|
80
|
+
def document_builder
|
81
|
+
document_builder_factory.namespace_aware = true
|
82
|
+
document_builder_factory.new_document_builder
|
83
|
+
end
|
84
|
+
|
85
|
+
def string_reader
|
86
|
+
StringReader.new(@string)
|
87
|
+
end
|
88
|
+
|
89
|
+
def input_source
|
90
|
+
InputSource.new(string_reader)
|
91
|
+
end
|
92
|
+
|
93
|
+
def parse_string
|
94
|
+
raise ParseError if @string.empty?
|
95
|
+
builder = document_builder
|
96
|
+
|
97
|
+
begin
|
98
|
+
jdoc = builder.parse(input_source)
|
99
|
+
rescue NativeException
|
100
|
+
raise ParseError
|
101
|
+
end
|
102
|
+
|
103
|
+
XML::Document.from_java(jdoc)
|
104
|
+
end
|
105
|
+
|
106
|
+
def parse_file
|
107
|
+
builder = document_builder
|
108
|
+
|
109
|
+
begin
|
110
|
+
jdoc = builder.parse(@filename)
|
111
|
+
rescue
|
112
|
+
raise ParseError
|
113
|
+
end
|
114
|
+
|
115
|
+
XML::Document.from_java(jdoc)
|
116
|
+
end
|
117
|
+
|
118
|
+
def parse_io
|
119
|
+
parse_string
|
120
|
+
end
|
121
|
+
end
|
@@ -0,0 +1,98 @@
|
|
1
|
+
module LibXMLJRuby
|
2
|
+
module XML
|
3
|
+
module XPath
|
4
|
+
NODESET = nil
|
5
|
+
|
6
|
+
class Object
|
7
|
+
include Enumerable
|
8
|
+
|
9
|
+
def initialize(expr, document, nslist = nil)
|
10
|
+
@expr, @document = expr, document
|
11
|
+
@nslist = nslist
|
12
|
+
end
|
13
|
+
|
14
|
+
def each(&block)
|
15
|
+
set.each(&block)
|
16
|
+
end
|
17
|
+
|
18
|
+
def length
|
19
|
+
set.length
|
20
|
+
end
|
21
|
+
|
22
|
+
def first
|
23
|
+
set.first
|
24
|
+
end
|
25
|
+
|
26
|
+
def xpath_type
|
27
|
+
XML::XPath::NODESET
|
28
|
+
end
|
29
|
+
|
30
|
+
def set
|
31
|
+
@set ||= XML::Node::Set.from_java(evaluate_expression)
|
32
|
+
end
|
33
|
+
|
34
|
+
def [](index)
|
35
|
+
set[index]
|
36
|
+
end
|
37
|
+
|
38
|
+
private
|
39
|
+
def xpath_factory
|
40
|
+
@xpath_factory ||= XPathFactory.new_instance
|
41
|
+
end
|
42
|
+
|
43
|
+
def xpath
|
44
|
+
@xpath ||= xpath_factory.newXPath
|
45
|
+
end
|
46
|
+
|
47
|
+
def resolver
|
48
|
+
PrefixResolverDefault.new(doc_element)
|
49
|
+
end
|
50
|
+
|
51
|
+
def doc_element
|
52
|
+
if document.respond_to?(:getDocumentElement)
|
53
|
+
document.getDocumentElement
|
54
|
+
elsif document.respond_to?(:getOwnerDocument)
|
55
|
+
document.getOwnerDocument
|
56
|
+
else
|
57
|
+
nil
|
58
|
+
end
|
59
|
+
end
|
60
|
+
|
61
|
+
def namespace_context
|
62
|
+
CustomNamespaceContext.new(resolver)
|
63
|
+
end
|
64
|
+
|
65
|
+
def evaluate_expression
|
66
|
+
xpath.setNamespaceContext(namespace_context)
|
67
|
+
xpath.evaluate(@expr, document, XPathConstants::NODESET)
|
68
|
+
end
|
69
|
+
|
70
|
+
def document
|
71
|
+
@document.respond_to?(:java_obj) ? @document.java_obj : @document
|
72
|
+
end
|
73
|
+
|
74
|
+
class CustomNamespaceContext
|
75
|
+
include javax.xml.namespace.NamespaceContext
|
76
|
+
|
77
|
+
attr_reader :resolver
|
78
|
+
|
79
|
+
def initialize(resolver)
|
80
|
+
@resolver = resolver
|
81
|
+
end
|
82
|
+
|
83
|
+
def getNamespaceURI(prefix)
|
84
|
+
resolver.getNamespaceForPrefix(prefix)
|
85
|
+
end
|
86
|
+
|
87
|
+
def getPrefixes(val)
|
88
|
+
nil
|
89
|
+
end
|
90
|
+
|
91
|
+
def getPrefix(uri)
|
92
|
+
nil
|
93
|
+
end
|
94
|
+
end
|
95
|
+
end
|
96
|
+
end
|
97
|
+
end
|
98
|
+
end
|
data/lib/libxml.rb
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
require 'libxml-jruby'
|
data/lib/xml.rb
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
# This file loads libxml and adds the LibXML namespace
|
2
|
+
# to the toplevel for conveneience. The end result
|
3
|
+
# is to have XML:: universally exposed.
|
4
|
+
#
|
5
|
+
# It is recommend that you only load this file for libs
|
6
|
+
# that do not have their own namespace, eg. administrative
|
7
|
+
# scripts, personal programs, etc. For other applications
|
8
|
+
# require 'libxml' instead and include LibXML into your
|
9
|
+
# app/libs namespace.
|
10
|
+
|
11
|
+
require 'libxml'
|
12
|
+
|
13
|
+
include LibXML
|
data/lib/xml/libxml.rb
ADDED
@@ -0,0 +1,19 @@
|
|
1
|
+
require 'xml'
|
2
|
+
|
3
|
+
1.times do |count|
|
4
|
+
|
5
|
+
xml_doc = XML::Document.new()
|
6
|
+
xml_doc.encoding = "UTF-8"
|
7
|
+
xml_doc.root = XML::Node.new("Request")
|
8
|
+
|
9
|
+
1000.times do |index|
|
10
|
+
xml_doc.root << node = XML::Node.new("row")
|
11
|
+
node["user_id"] = index.to_s
|
12
|
+
node << "600445"
|
13
|
+
end
|
14
|
+
|
15
|
+
xml_str = xml_doc.to_s
|
16
|
+
print "\r#{count}"
|
17
|
+
$stdout.flush
|
18
|
+
end
|
19
|
+
puts "\n"
|
@@ -0,0 +1,21 @@
|
|
1
|
+
require 'xml'
|
2
|
+
|
3
|
+
def test( doc2 )
|
4
|
+
doc = XML::Document.new('1.0')
|
5
|
+
doc.root = XML::Node.new("ccc")
|
6
|
+
doc.root['aaa'] = 'aaa'
|
7
|
+
doc.root.child_add(doc2.root.copy(true)) # BUG!
|
8
|
+
doc.root << doc2.root.copy(true)
|
9
|
+
return doc
|
10
|
+
end
|
11
|
+
|
12
|
+
def test2
|
13
|
+
doc2 = XML::Document.new('1.0')
|
14
|
+
doc2.root = XML::Node.new("aaa")
|
15
|
+
test( doc2 )
|
16
|
+
end
|
17
|
+
|
18
|
+
1000.times { |i|
|
19
|
+
print "\r#{i}"; $stdout.flush
|
20
|
+
test2
|
21
|
+
}
|
@@ -0,0 +1,38 @@
|
|
1
|
+
require 'xml'
|
2
|
+
|
3
|
+
str = <<-STR
|
4
|
+
<html>
|
5
|
+
<body>
|
6
|
+
<div class="textarea" id="t1"
|
7
|
+
style="STATIC">werwerwerwerwer </div>
|
8
|
+
<div class="textarea" id="t2" style="STATIC">
|
9
|
+
Quisque et diam dapibus nisi bibendum blandit.
|
10
|
+
</div>
|
11
|
+
<div class="textarea" id="t3" style="STATIC">
|
12
|
+
<p>aaaaaaaaa</p>
|
13
|
+
</div>
|
14
|
+
</body>
|
15
|
+
</html>
|
16
|
+
STR
|
17
|
+
|
18
|
+
XML::Parser.default_keep_blanks = false
|
19
|
+
xp = XML::Parser.new
|
20
|
+
xp.string = str
|
21
|
+
doc = xp.parse
|
22
|
+
|
23
|
+
xpath = "//div[@id='t1']"
|
24
|
+
div1 = doc.find(xpath).to_a[0]
|
25
|
+
printf "xxx div1: #{div1}\n"
|
26
|
+
|
27
|
+
xpath = "//div[@id='t2']"
|
28
|
+
div2 = doc.find(xpath).to_a[0]
|
29
|
+
printf "xxx div2: #{div2}\n"
|
30
|
+
|
31
|
+
|
32
|
+
div2.each do |child|
|
33
|
+
#c = child.clone
|
34
|
+
c = child.copy(false)
|
35
|
+
div1.child_add(c)
|
36
|
+
end
|
37
|
+
|
38
|
+
printf "xxx root: #{doc.root}\n"
|
@@ -0,0 +1,15 @@
|
|
1
|
+
require 'xml'
|
2
|
+
|
3
|
+
# This is related to bug 8337, complaint is on amd64/fbsd
|
4
|
+
# unknown if it happens on other amd64/os combos
|
5
|
+
|
6
|
+
Process.setrlimit(Process::RLIMIT_NOFILE,10005)
|
7
|
+
|
8
|
+
(1..10000).each{|time|
|
9
|
+
XML::Document.file(File.join(File.dirname(__FILE__),'ets_test.xml'))
|
10
|
+
if time % 100 == 0
|
11
|
+
print "\r#{time}"
|
12
|
+
$stdout.flush
|
13
|
+
end
|
14
|
+
}
|
15
|
+
puts "\n"
|
@@ -0,0 +1,21 @@
|
|
1
|
+
require 'xml'
|
2
|
+
|
3
|
+
100.times do |count|
|
4
|
+
|
5
|
+
xml_doc = XML::Document.new()
|
6
|
+
xml_doc.encoding = "UTF-8"
|
7
|
+
xml_doc.root = XML::Node.new("Request")
|
8
|
+
|
9
|
+
1000.times do |index|
|
10
|
+
|
11
|
+
xml_doc.root << node = XML::Node.new("row")
|
12
|
+
node["user_id"] = index.to_s
|
13
|
+
node << "600445"
|
14
|
+
|
15
|
+
end
|
16
|
+
|
17
|
+
xml_str = xml_doc.to_s
|
18
|
+
print "\r#{count}"
|
19
|
+
$stdout.flush
|
20
|
+
end
|
21
|
+
puts "\n"
|
data/test/ets_gpx.rb
ADDED
@@ -0,0 +1,26 @@
|
|
1
|
+
require 'libxml'
|
2
|
+
|
3
|
+
100.times do
|
4
|
+
doc = XML::Document.new
|
5
|
+
doc.encoding = 'UTF-8'
|
6
|
+
|
7
|
+
root = XML::Node.new 'gpx'
|
8
|
+
root['version'] = '1.0'
|
9
|
+
root['creator'] = 'OpenStreetMap.org'
|
10
|
+
root['xmlns'] = "http://www.topografix.com/GPX/1/0/"
|
11
|
+
|
12
|
+
doc.root = root
|
13
|
+
|
14
|
+
track = XML::Node.new 'trk'
|
15
|
+
doc.root << track
|
16
|
+
|
17
|
+
trkseg = XML::Node.new 'trkseg'
|
18
|
+
track << trkseg
|
19
|
+
|
20
|
+
1.upto(1000) do |n|
|
21
|
+
trkpt = XML::Node.new 'trkpt'
|
22
|
+
trkpt['lat'] = n.to_s
|
23
|
+
trkpt['lon'] = n.to_s
|
24
|
+
trkseg << trkpt
|
25
|
+
end
|
26
|
+
end
|
data/test/ets_node_gc.rb
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
require 'xml'
|
2
|
+
|
3
|
+
# test of bug 13310, clears MEM2
|
4
|
+
|
5
|
+
include GC
|
6
|
+
|
7
|
+
inner = XML::Node.new('inner')
|
8
|
+
save = nil
|
9
|
+
1.times do
|
10
|
+
outer = XML::Node.new('outer')
|
11
|
+
outer.child = inner
|
12
|
+
1.times do
|
13
|
+
doc = XML::Document.new
|
14
|
+
doc.root = outer
|
15
|
+
# Uncomment the following line and it won't crash
|
16
|
+
save = doc
|
17
|
+
end
|
18
|
+
garbage_collect
|
19
|
+
end
|
20
|
+
garbage_collect
|
21
|
+
puts inner
|