libxml-ruby 5.0.6 → 6.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/{HISTORY → CHANGELOG.md} +875 -930
- data/LICENSE +20 -20
- data/README.md +67 -0
- data/Rakefile +13 -34
- data/ext/libxml/extconf.rb +34 -20
- data/ext/libxml/libxml.c +2 -14
- data/ext/libxml/ruby_libxml.h +1 -1
- data/ext/libxml/ruby_xml_attr.c +27 -22
- data/ext/libxml/ruby_xml_attr.h +1 -0
- data/ext/libxml/ruby_xml_attr_decl.c +19 -12
- data/ext/libxml/ruby_xml_attributes.c +18 -9
- data/ext/libxml/ruby_xml_document.c +111 -98
- data/ext/libxml/ruby_xml_document.h +1 -0
- data/ext/libxml/ruby_xml_dtd.c +49 -19
- data/ext/libxml/ruby_xml_dtd.h +1 -0
- data/ext/libxml/ruby_xml_html_parser.c +1 -1
- data/ext/libxml/ruby_xml_html_parser_context.c +19 -6
- data/ext/libxml/ruby_xml_html_parser_context.h +1 -0
- data/ext/libxml/ruby_xml_input_cbg.c +45 -17
- data/ext/libxml/ruby_xml_io.c +3 -1
- data/ext/libxml/ruby_xml_namespace.c +20 -12
- data/ext/libxml/ruby_xml_namespace.h +1 -0
- data/ext/libxml/ruby_xml_namespaces.c +40 -20
- data/ext/libxml/ruby_xml_node.c +71 -32
- data/ext/libxml/ruby_xml_node.h +2 -0
- data/ext/libxml/ruby_xml_parser.c +1 -1
- data/ext/libxml/ruby_xml_parser_context.c +54 -47
- data/ext/libxml/ruby_xml_parser_context.h +1 -0
- data/ext/libxml/ruby_xml_reader.c +25 -15
- data/ext/libxml/ruby_xml_registry.c +31 -0
- data/ext/libxml/ruby_xml_registry.h +22 -0
- data/ext/libxml/ruby_xml_relaxng.c +21 -5
- data/ext/libxml/ruby_xml_relaxng.h +1 -0
- data/ext/libxml/ruby_xml_sax_parser.c +1 -1
- data/ext/libxml/ruby_xml_schema.c +18 -11
- data/ext/libxml/ruby_xml_schema.h +1 -0
- data/ext/libxml/ruby_xml_schema_attribute.c +7 -7
- data/ext/libxml/ruby_xml_schema_element.c +8 -8
- data/ext/libxml/ruby_xml_schema_facet.c +7 -7
- data/ext/libxml/ruby_xml_schema_type.c +12 -19
- data/ext/libxml/ruby_xml_version.h +4 -4
- data/ext/libxml/ruby_xml_writer.c +18 -6
- data/ext/libxml/ruby_xml_xpath.c +2 -2
- data/ext/libxml/ruby_xml_xpath.h +1 -1
- data/ext/libxml/ruby_xml_xpath_context.c +72 -26
- data/ext/libxml/ruby_xml_xpath_expression.c +11 -5
- data/ext/libxml/ruby_xml_xpath_expression.h +1 -0
- data/ext/libxml/ruby_xml_xpath_object.c +69 -54
- data/ext/libxml/ruby_xml_xpath_object.h +3 -1
- data/ext/vc/libxml_ruby/libxml_ruby.vcxproj +271 -0
- data/ext/xcode/libxml-ruby.xcodeproj/project.pbxproj +633 -0
- data/ext/xcode/libxml-ruby.xcodeproj/project.xcworkspace/contents.xcworkspacedata +7 -0
- data/ext/xcode/libxml-ruby.xcodeproj/project.xcworkspace/xcshareddata/IDEWorkspaceChecks.plist +8 -0
- data/ext/xcode/libxml-ruby.xcodeproj/xcshareddata/xcschemes/libxml-ruby.xcscheme +80 -0
- data/lib/libxml/document.rb +0 -29
- data/lib/libxml/error.rb +30 -3
- data/lib/libxml/html_parser.rb +0 -16
- data/lib/libxml/node.rb +1 -3
- data/lib/libxml/parser.rb +0 -8
- data/lib/libxml/schema/attribute.rb +27 -19
- data/lib/libxml/schema/element.rb +20 -0
- data/lib/libxml/schema/type.rb +44 -21
- data/lib/libxml/schema.rb +47 -47
- data/lib/libxml-ruby.rb +30 -30
- data/libxml-ruby.gemspec +12 -16
- data/test/c14n/result/1-1-without-comments/example-1 +3 -3
- data/test/c14n/result/1-1-without-comments/example-2 +10 -10
- data/test/c14n/result/1-1-without-comments/example-3 +13 -13
- data/test/c14n/result/1-1-without-comments/example-4 +8 -8
- data/test/c14n/result/1-1-without-comments/example-5 +2 -2
- data/test/c14n/result/with-comments/example-1 +5 -5
- data/test/c14n/result/with-comments/example-2 +10 -10
- data/test/c14n/result/with-comments/example-3 +13 -13
- data/test/c14n/result/with-comments/example-4 +8 -8
- data/test/c14n/result/with-comments/example-5 +3 -3
- data/test/c14n/result/without-comments/example-1 +3 -3
- data/test/c14n/result/without-comments/example-2 +10 -10
- data/test/c14n/result/without-comments/example-3 +13 -13
- data/test/c14n/result/without-comments/example-4 +8 -8
- data/test/c14n/result/without-comments/example-5 +2 -2
- data/test/test_attr.rb +179 -180
- data/test/test_attr_decl.rb +131 -131
- data/test/test_attributes.rb +135 -135
- data/test/test_canonicalize.rb +122 -120
- data/test/test_document.rb +2 -4
- data/test/test_dtd.rb +12 -4
- data/test/test_encoding_sax.rb +114 -114
- data/test/test_error.rb +1 -1
- data/test/test_html_parser.rb +6 -2
- data/test/test_html_parser_context.rb +22 -22
- data/test/test_input_callbacks.rb +36 -0
- data/test/test_namespace.rb +1 -1
- data/test/test_namespaces.rb +200 -200
- data/test/test_node.rb +16 -0
- data/test/test_node_cdata.rb +50 -50
- data/test/test_node_comment.rb +32 -32
- data/test/test_node_copy.rb +40 -40
- data/test/test_node_edit.rb +176 -158
- data/test/test_node_pi.rb +37 -37
- data/test/test_node_text.rb +69 -69
- data/test/test_node_xlink.rb +28 -28
- data/test/test_parser.rb +5 -41
- data/test/test_parser_context.rb +198 -198
- data/test/test_properties.rb +38 -38
- data/test/test_reader.rb +55 -6
- data/test/test_relaxng.rb +59 -53
- data/test/test_sax_parser.rb +345 -345
- data/test/test_schema.rb +28 -0
- data/test/test_traversal.rb +152 -152
- data/test/test_writer.rb +0 -31
- data/test/test_xinclude.rb +20 -20
- data/test/test_xml.rb +3 -7
- data/test/test_xpath.rb +244 -244
- data/test/test_xpath_context.rb +87 -87
- data/test/test_xpath_expression.rb +37 -37
- metadata +32 -25
- data/README.rdoc +0 -208
- data/ext/libxml/extconf.h +0 -4
- data/ext/libxml/ruby_xml_cbg.c +0 -85
- data/lib/libxml/hpricot.rb +0 -78
- data/lib/libxml.rb +0 -5
- data/lib/xml/libxml.rb +0 -10
- data/lib/xml.rb +0 -14
- data/script/benchmark/depixelate +0 -634
- data/script/benchmark/hamlet.xml +0 -9055
- data/script/benchmark/parsecount +0 -170
- data/script/benchmark/sock_entries.xml +0 -507
- data/script/benchmark/throughput +0 -41
- data/script/test +0 -6
- data/test/test_deprecated_require.rb +0 -12
|
@@ -1,37 +1,37 @@
|
|
|
1
|
-
# encoding: UTF-8
|
|
2
|
-
|
|
3
|
-
require_relative './test_helper'
|
|
4
|
-
|
|
5
|
-
|
|
6
|
-
class TestXPathExpression < Minitest::Test
|
|
7
|
-
def setup
|
|
8
|
-
xp = LibXML::XML::Parser.string('<ruby_array uga="booga" foo="bar"><fixnum>one</fixnum><fixnum>two</fixnum></ruby_array>')
|
|
9
|
-
@doc = xp.parse
|
|
10
|
-
end
|
|
11
|
-
|
|
12
|
-
def teardown
|
|
13
|
-
@doc = nil
|
|
14
|
-
end
|
|
15
|
-
|
|
16
|
-
def test_nodes
|
|
17
|
-
expr = LibXML::XML::XPath::Expression.compile('/ruby_array/fixnum')
|
|
18
|
-
set = @doc.find(expr)
|
|
19
|
-
assert_instance_of(LibXML::XML::XPath::Object, set)
|
|
20
|
-
assert_equal(2, set.size)
|
|
21
|
-
end
|
|
22
|
-
|
|
23
|
-
def test_find_class
|
|
24
|
-
expr = LibXML::XML::XPath::Expression.new('/ruby_array/fixnum')
|
|
25
|
-
set = @doc.find(expr)
|
|
26
|
-
assert_instance_of(LibXML::XML::XPath::Object, set)
|
|
27
|
-
assert_equal(2, set.size)
|
|
28
|
-
end
|
|
29
|
-
|
|
30
|
-
def test_find_invalid
|
|
31
|
-
error = assert_raises(TypeError) do
|
|
32
|
-
@doc.find(999)
|
|
33
|
-
end
|
|
34
|
-
assert_equal('Argument should be an instance of a String or XPath::Expression',
|
|
35
|
-
error.to_s)
|
|
36
|
-
end
|
|
37
|
-
end
|
|
1
|
+
# encoding: UTF-8
|
|
2
|
+
|
|
3
|
+
require_relative './test_helper'
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
class TestXPathExpression < Minitest::Test
|
|
7
|
+
def setup
|
|
8
|
+
xp = LibXML::XML::Parser.string('<ruby_array uga="booga" foo="bar"><fixnum>one</fixnum><fixnum>two</fixnum></ruby_array>')
|
|
9
|
+
@doc = xp.parse
|
|
10
|
+
end
|
|
11
|
+
|
|
12
|
+
def teardown
|
|
13
|
+
@doc = nil
|
|
14
|
+
end
|
|
15
|
+
|
|
16
|
+
def test_nodes
|
|
17
|
+
expr = LibXML::XML::XPath::Expression.compile('/ruby_array/fixnum')
|
|
18
|
+
set = @doc.find(expr)
|
|
19
|
+
assert_instance_of(LibXML::XML::XPath::Object, set)
|
|
20
|
+
assert_equal(2, set.size)
|
|
21
|
+
end
|
|
22
|
+
|
|
23
|
+
def test_find_class
|
|
24
|
+
expr = LibXML::XML::XPath::Expression.new('/ruby_array/fixnum')
|
|
25
|
+
set = @doc.find(expr)
|
|
26
|
+
assert_instance_of(LibXML::XML::XPath::Object, set)
|
|
27
|
+
assert_equal(2, set.size)
|
|
28
|
+
end
|
|
29
|
+
|
|
30
|
+
def test_find_invalid
|
|
31
|
+
error = assert_raises(TypeError) do
|
|
32
|
+
@doc.find(999)
|
|
33
|
+
end
|
|
34
|
+
assert_equal('Argument should be an instance of a String or XPath::Expression',
|
|
35
|
+
error.to_s)
|
|
36
|
+
end
|
|
37
|
+
end
|
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: libxml-ruby
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version:
|
|
4
|
+
version: 6.0.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Ross Bamform
|
|
@@ -13,7 +13,7 @@ authors:
|
|
|
13
13
|
- Ryan Johnson
|
|
14
14
|
bindir: bin
|
|
15
15
|
cert_chain: []
|
|
16
|
-
date:
|
|
16
|
+
date: 1980-01-02 00:00:00.000000000 Z
|
|
17
17
|
dependencies:
|
|
18
18
|
- !ruby/object:Gem::Dependency
|
|
19
19
|
name: logger
|
|
@@ -57,22 +57,33 @@ dependencies:
|
|
|
57
57
|
- - ">="
|
|
58
58
|
- !ruby/object:Gem::Version
|
|
59
59
|
version: '0'
|
|
60
|
-
|
|
61
|
-
|
|
62
|
-
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
|
|
60
|
+
- !ruby/object:Gem::Dependency
|
|
61
|
+
name: rdoc
|
|
62
|
+
requirement: !ruby/object:Gem::Requirement
|
|
63
|
+
requirements:
|
|
64
|
+
- - ">="
|
|
65
|
+
- !ruby/object:Gem::Version
|
|
66
|
+
version: '0'
|
|
67
|
+
type: :development
|
|
68
|
+
prerelease: false
|
|
69
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
70
|
+
requirements:
|
|
71
|
+
- - ">="
|
|
72
|
+
- !ruby/object:Gem::Version
|
|
73
|
+
version: '0'
|
|
74
|
+
description: " libxml-Ruby provides Ruby language bindings for libxml2 It is free
|
|
75
|
+
software, \n released under the MIT License. libxml-ruby provides DOM, SAX, Reader,
|
|
76
|
+
and \n Writer APIs along with XPath support and validation via DTD, RelaxNG,
|
|
77
|
+
and XML Schema.\n"
|
|
66
78
|
executables: []
|
|
67
79
|
extensions:
|
|
68
80
|
- ext/libxml/extconf.rb
|
|
69
81
|
extra_rdoc_files: []
|
|
70
82
|
files:
|
|
71
|
-
-
|
|
83
|
+
- CHANGELOG.md
|
|
72
84
|
- LICENSE
|
|
73
|
-
- README.
|
|
85
|
+
- README.md
|
|
74
86
|
- Rakefile
|
|
75
|
-
- ext/libxml/extconf.h
|
|
76
87
|
- ext/libxml/extconf.rb
|
|
77
88
|
- ext/libxml/libxml.c
|
|
78
89
|
- ext/libxml/libxml_ruby.def
|
|
@@ -85,7 +96,6 @@ files:
|
|
|
85
96
|
- ext/libxml/ruby_xml_attr_decl.h
|
|
86
97
|
- ext/libxml/ruby_xml_attributes.c
|
|
87
98
|
- ext/libxml/ruby_xml_attributes.h
|
|
88
|
-
- ext/libxml/ruby_xml_cbg.c
|
|
89
99
|
- ext/libxml/ruby_xml_document.c
|
|
90
100
|
- ext/libxml/ruby_xml_document.h
|
|
91
101
|
- ext/libxml/ruby_xml_dtd.c
|
|
@@ -118,6 +128,8 @@ files:
|
|
|
118
128
|
- ext/libxml/ruby_xml_parser_options.h
|
|
119
129
|
- ext/libxml/ruby_xml_reader.c
|
|
120
130
|
- ext/libxml/ruby_xml_reader.h
|
|
131
|
+
- ext/libxml/ruby_xml_registry.c
|
|
132
|
+
- ext/libxml/ruby_xml_registry.h
|
|
121
133
|
- ext/libxml/ruby_xml_relaxng.c
|
|
122
134
|
- ext/libxml/ruby_xml_relaxng.h
|
|
123
135
|
- ext/libxml/ruby_xml_sax2_handler.c
|
|
@@ -148,14 +160,17 @@ files:
|
|
|
148
160
|
- ext/libxml/ruby_xml_xpath_object.c
|
|
149
161
|
- ext/libxml/ruby_xml_xpath_object.h
|
|
150
162
|
- ext/vc/libxml_ruby.sln
|
|
163
|
+
- ext/vc/libxml_ruby/libxml_ruby.vcxproj
|
|
164
|
+
- ext/xcode/libxml-ruby.xcodeproj/project.pbxproj
|
|
165
|
+
- ext/xcode/libxml-ruby.xcodeproj/project.xcworkspace/contents.xcworkspacedata
|
|
166
|
+
- ext/xcode/libxml-ruby.xcodeproj/project.xcworkspace/xcshareddata/IDEWorkspaceChecks.plist
|
|
167
|
+
- ext/xcode/libxml-ruby.xcodeproj/xcshareddata/xcschemes/libxml-ruby.xcscheme
|
|
151
168
|
- lib/libxml-ruby.rb
|
|
152
|
-
- lib/libxml.rb
|
|
153
169
|
- lib/libxml/attr.rb
|
|
154
170
|
- lib/libxml/attr_decl.rb
|
|
155
171
|
- lib/libxml/attributes.rb
|
|
156
172
|
- lib/libxml/document.rb
|
|
157
173
|
- lib/libxml/error.rb
|
|
158
|
-
- lib/libxml/hpricot.rb
|
|
159
174
|
- lib/libxml/html_parser.rb
|
|
160
175
|
- lib/libxml/namespace.rb
|
|
161
176
|
- lib/libxml/namespaces.rb
|
|
@@ -168,15 +183,7 @@ files:
|
|
|
168
183
|
- lib/libxml/schema/element.rb
|
|
169
184
|
- lib/libxml/schema/type.rb
|
|
170
185
|
- lib/libxml/tree.rb
|
|
171
|
-
- lib/xml.rb
|
|
172
|
-
- lib/xml/libxml.rb
|
|
173
186
|
- libxml-ruby.gemspec
|
|
174
|
-
- script/benchmark/depixelate
|
|
175
|
-
- script/benchmark/hamlet.xml
|
|
176
|
-
- script/benchmark/parsecount
|
|
177
|
-
- script/benchmark/sock_entries.xml
|
|
178
|
-
- script/benchmark/throughput
|
|
179
|
-
- script/test
|
|
180
187
|
- test/c14n/given/doc.dtd
|
|
181
188
|
- test/c14n/given/example-1.xml
|
|
182
189
|
- test/c14n/given/example-2.xml
|
|
@@ -232,7 +239,6 @@ files:
|
|
|
232
239
|
- test/test_attr_decl.rb
|
|
233
240
|
- test/test_attributes.rb
|
|
234
241
|
- test/test_canonicalize.rb
|
|
235
|
-
- test/test_deprecated_require.rb
|
|
236
242
|
- test/test_document.rb
|
|
237
243
|
- test/test_document_write.rb
|
|
238
244
|
- test/test_dtd.rb
|
|
@@ -242,6 +248,7 @@ files:
|
|
|
242
248
|
- test/test_helper.rb
|
|
243
249
|
- test/test_html_parser.rb
|
|
244
250
|
- test/test_html_parser_context.rb
|
|
251
|
+
- test/test_input_callbacks.rb
|
|
245
252
|
- test/test_namespace.rb
|
|
246
253
|
- test/test_namespaces.rb
|
|
247
254
|
- test/test_node.rb
|
|
@@ -279,7 +286,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
|
279
286
|
requirements:
|
|
280
287
|
- - ">="
|
|
281
288
|
- !ruby/object:Gem::Version
|
|
282
|
-
version: '2
|
|
289
|
+
version: '3.2'
|
|
283
290
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
|
284
291
|
requirements:
|
|
285
292
|
- - ">="
|
|
@@ -294,7 +301,6 @@ test_files:
|
|
|
294
301
|
- test/test_attr_decl.rb
|
|
295
302
|
- test/test_attributes.rb
|
|
296
303
|
- test/test_canonicalize.rb
|
|
297
|
-
- test/test_deprecated_require.rb
|
|
298
304
|
- test/test_document.rb
|
|
299
305
|
- test/test_document_write.rb
|
|
300
306
|
- test/test_dtd.rb
|
|
@@ -304,6 +310,7 @@ test_files:
|
|
|
304
310
|
- test/test_helper.rb
|
|
305
311
|
- test/test_html_parser.rb
|
|
306
312
|
- test/test_html_parser_context.rb
|
|
313
|
+
- test/test_input_callbacks.rb
|
|
307
314
|
- test/test_namespace.rb
|
|
308
315
|
- test/test_namespaces.rb
|
|
309
316
|
- test/test_node.rb
|
data/README.rdoc
DELETED
|
@@ -1,208 +0,0 @@
|
|
|
1
|
-
= LibXML Ruby
|
|
2
|
-
|
|
3
|
-
== Overview
|
|
4
|
-
The libxml gem provides Ruby language bindings for GNOME's Libxml2
|
|
5
|
-
XML toolkit. It is free software, released under the MIT License.
|
|
6
|
-
|
|
7
|
-
We think libxml-ruby is the best XML library for Ruby because:
|
|
8
|
-
|
|
9
|
-
* Speed - Its much faster than REXML and Hpricot
|
|
10
|
-
* Features - It provides an amazing number of featues
|
|
11
|
-
* Conformance - It passes all 1800+ tests from the OASIS XML Tests Suite
|
|
12
|
-
|
|
13
|
-
== Requirements
|
|
14
|
-
libxml-ruby requires Ruby 3.0.0 or higher. It depends on libxml2 to
|
|
15
|
-
function properly. libxml2, in turn, depends on:
|
|
16
|
-
|
|
17
|
-
* libm (math routines: very standard)
|
|
18
|
-
* libz (zlib)
|
|
19
|
-
* libiconv
|
|
20
|
-
|
|
21
|
-
If you are running Linux or Unix you'll need a C compiler so the
|
|
22
|
-
extension can be compiled when it is installed. If you are running
|
|
23
|
-
Windows, then install the x64-mingw-ucr gem or build it yourself using (Ruby
|
|
24
|
-
for Windows)[https://rubyinstaller.org/] or directly with msys2[https://msys2.github.io/]
|
|
25
|
-
and ucrt64.
|
|
26
|
-
|
|
27
|
-
== Installation
|
|
28
|
-
The easiest way to install libxml-ruby is via RubyGems. To install:
|
|
29
|
-
|
|
30
|
-
<tt>gem install libxml-ruby</tt>
|
|
31
|
-
|
|
32
|
-
If the extension compile process cannot find libxml2, you may need to indicate
|
|
33
|
-
the location of the libxml2 configuration utility as it is used to find the
|
|
34
|
-
required header and include files. (If you need to indicate a location for the
|
|
35
|
-
libxml2 library or header files different than reported by <tt>xml2-config</tt>,
|
|
36
|
-
see the additional configuration options.)
|
|
37
|
-
|
|
38
|
-
This may be done with RubyGems:
|
|
39
|
-
|
|
40
|
-
<tt>gem install libxml-ruby -- --with-xml2-dir=/path/to/xml2-config</tt>
|
|
41
|
-
|
|
42
|
-
Or bundler:
|
|
43
|
-
|
|
44
|
-
<tt>bundle config build.libxml-ruby --with-xml2-config=/path/to/xml2-config</tt>
|
|
45
|
-
|
|
46
|
-
<tt>bundle install libxml-ruby</tt>
|
|
47
|
-
|
|
48
|
-
If you are running Windows, then install the libxml-ruby-x64-mingw32 gem.
|
|
49
|
-
The gem includes prebuilt extensions for Ruby 3.2 and 3.3.
|
|
50
|
-
|
|
51
|
-
The gem also includes a Microsoft VC++ solution and XCode project - these
|
|
52
|
-
are very useful for debugging.
|
|
53
|
-
|
|
54
|
-
libxml-ruby's source codes lives on GitHub[https://github.com/xml4r/libxml-ruby].
|
|
55
|
-
|
|
56
|
-
== Getting Started
|
|
57
|
-
Using libxml is easy. First decide what parser you want to use:
|
|
58
|
-
|
|
59
|
-
* Generally you'll want to use the LibXML::XML::Parser which provides a tree based API.
|
|
60
|
-
* For larger documents that don't fit into memory, or if you prefer an input based API, use the LibXML::XML::Reader.
|
|
61
|
-
* To parse HTML files use LibXML::XML::HTMLParser.
|
|
62
|
-
* If you are masochistic, then use the LibXML::XML::SaxParser, which provides a callback API.
|
|
63
|
-
|
|
64
|
-
Once you have chosen a parser, choose a datasource. Libxml can parse files, strings, URIs
|
|
65
|
-
and IO streams. For each data source you can specify an LibXML::XML::Encoding, a base uri and
|
|
66
|
-
various parser options. For more information, refer the LibXML::XML::Parser.document,
|
|
67
|
-
LibXML::XML::Parser.file, LibXML::XML::Parser.io or LibXML:::XML::Parser.string methods (the
|
|
68
|
-
same methods are defined on all four parser classes).
|
|
69
|
-
|
|
70
|
-
== Advanced Functionality
|
|
71
|
-
Beyond the basics of parsing and processing XML and HTML documents,
|
|
72
|
-
libxml provides a wealth of additional functionality.
|
|
73
|
-
|
|
74
|
-
Most commonly, you'll want to use its LibXML::XML::XPath support, which makes
|
|
75
|
-
it easy to find data inside an XML document. Although not as popular,
|
|
76
|
-
LibXML::XML::XPointer provides another API for finding data inside an XML document.
|
|
77
|
-
|
|
78
|
-
Often times you'll need to validate data before processing it. For example,
|
|
79
|
-
if you accept user generated content submitted over the Web, you'll
|
|
80
|
-
want to verify that it does not contain malicious code such as embedded scripts.
|
|
81
|
-
This can be done using libxml's powerful set of validators:
|
|
82
|
-
|
|
83
|
-
* DTDs (LibXML::XML::Dtd)
|
|
84
|
-
* Relax Schemas (LibXML::XML::RelaxNG)
|
|
85
|
-
* XML Schema (LibXML::XML::Schema)
|
|
86
|
-
|
|
87
|
-
Finally, if you'd like to use XSL Transformations to process data, then install
|
|
88
|
-
the {libxslt gem}[https://github.com/xml4r/libxslt-rubygem].
|
|
89
|
-
|
|
90
|
-
== Usage
|
|
91
|
-
For information about using libxml-ruby please refer to its
|
|
92
|
-
documentation[https://xml4r.github.io/libxml-ruby]. Some tutorials are also
|
|
93
|
-
available[https://github.com/xml4r/libxml-ruby/wiki].
|
|
94
|
-
|
|
95
|
-
All libxml classes are in the LibXML::XML module. The easiest
|
|
96
|
-
way to use libxml is to <tt>require 'xml'</tt>. This will mixin
|
|
97
|
-
the LibXML module into the global namespace, allowing you to
|
|
98
|
-
write code like this:
|
|
99
|
-
|
|
100
|
-
require 'xml'
|
|
101
|
-
document = XML::Document.new
|
|
102
|
-
|
|
103
|
-
However, when creating an application or library you plan to
|
|
104
|
-
redistribute, it is best to not add the LibXML module to the global
|
|
105
|
-
namespace, in which case you can either write your code like this:
|
|
106
|
-
|
|
107
|
-
require 'libxml'
|
|
108
|
-
document = LibXML::XML::Document.new
|
|
109
|
-
|
|
110
|
-
Or you can utilize a namespace for your own work and include LibXML into it.
|
|
111
|
-
For example:
|
|
112
|
-
|
|
113
|
-
require 'libxml'
|
|
114
|
-
|
|
115
|
-
module MyApplication
|
|
116
|
-
include LibXML
|
|
117
|
-
|
|
118
|
-
class MyClass
|
|
119
|
-
def some_method
|
|
120
|
-
document = XML::Document.new
|
|
121
|
-
end
|
|
122
|
-
end
|
|
123
|
-
end
|
|
124
|
-
|
|
125
|
-
For simplicity's sake, the documentation uses the xml module in its examples.
|
|
126
|
-
|
|
127
|
-
== Tests
|
|
128
|
-
|
|
129
|
-
To run tests you first need to build the shared libary:
|
|
130
|
-
|
|
131
|
-
rake compile
|
|
132
|
-
|
|
133
|
-
Once you have build the shared libary, you can then run tests using rake:
|
|
134
|
-
|
|
135
|
-
rake test
|
|
136
|
-
|
|
137
|
-
+Build status: {rdoc-image:https://github.com/xml4r/libxml-ruby/actions/workflows/mri.yml/badge.svg}[https://github.com/xml4r/libxml-ruby/actions/workflows/mri.yml]
|
|
138
|
-
|
|
139
|
-
== Performance
|
|
140
|
-
|
|
141
|
-
In addition to being feature rich and conformation, the main reason
|
|
142
|
-
people use libxml-ruby is for performance. Here are the results
|
|
143
|
-
of a couple simple benchmarks recently blogged about on the
|
|
144
|
-
Web (you can find them in the benchmark directory of the
|
|
145
|
-
libxml distribution).
|
|
146
|
-
|
|
147
|
-
From http://depixelate.com/2008/4/23/ruby-xml-parsing-benchmarks
|
|
148
|
-
|
|
149
|
-
user system total real
|
|
150
|
-
libxml 0.032000 0.000000 0.032000 ( 0.031000)
|
|
151
|
-
Hpricot 0.640000 0.031000 0.671000 ( 0.890000)
|
|
152
|
-
REXML 1.813000 0.047000 1.860000 ( 2.031000)
|
|
153
|
-
|
|
154
|
-
From https://svn.concord.org/svn/projects/trunk/common/ruby/xml_benchmarks/
|
|
155
|
-
|
|
156
|
-
user system total real
|
|
157
|
-
libxml 0.641000 0.031000 0.672000 ( 0.672000)
|
|
158
|
-
hpricot 5.359000 0.062000 5.421000 ( 5.516000)
|
|
159
|
-
rexml 22.859000 0.047000 22.906000 ( 23.203000)
|
|
160
|
-
|
|
161
|
-
|
|
162
|
-
== Documentation
|
|
163
|
-
Documentation is available via rdoc, and is installed automatically with the
|
|
164
|
-
gem.
|
|
165
|
-
|
|
166
|
-
libxml-ruby's {online
|
|
167
|
-
documentation}[https://xml4r.github.io/libxml-ruby/rdoc/index.html] is generated
|
|
168
|
-
using Hanna, which is a development gem dependency.
|
|
169
|
-
|
|
170
|
-
Note that older versions of Rdoc, which ship with Ruby 1.8.x, will report
|
|
171
|
-
a number of errors. To avoid them, install Rdoc 2.1 or higher. Once you have
|
|
172
|
-
installed the gem, you'll have to disable the version of Rdoc that Ruby 1.8.x
|
|
173
|
-
includes. An easy way to do that is rename the directory
|
|
174
|
-
<tt>ruby/lib/ruby/1.8/rdoc</tt> to
|
|
175
|
-
<tt>ruby/lib/ruby/1.8/rdoc_old</tt>.
|
|
176
|
-
|
|
177
|
-
== Support
|
|
178
|
-
If you have any questions about using libxml-ruby, please report an issue
|
|
179
|
-
on GitHub[https://github.com/xml4r/libxml-ruby/issues].
|
|
180
|
-
|
|
181
|
-
== Memory Management
|
|
182
|
-
libxml-ruby automatically manages memory associated with the
|
|
183
|
-
underlying libxml2 library. The bindings create a one-to-one mapping between
|
|
184
|
-
Ruby objects and libxml documents and libxml parent nodes (ie, nodes that do not
|
|
185
|
-
have a parent and do not belong to a document). In these cases,
|
|
186
|
-
the bindings manage the memory. They do this by installing a free
|
|
187
|
-
function and storing a back pointer to the Ruby object from the xmlnode
|
|
188
|
-
using the _private member on libxml structures. When the Ruby object
|
|
189
|
-
goes out of scope, the underlying libxml structure is freed. Libxml
|
|
190
|
-
itself then frees all child nodes (recursively).
|
|
191
|
-
|
|
192
|
-
For all other nodes (the vast majority), the bindings create temporary
|
|
193
|
-
Ruby objects that get freed once they go out of scope. Thus there can be
|
|
194
|
-
more than one Ruby object pointing to the same xml node. To mostly hide
|
|
195
|
-
this from a programmer on the Ruby side, the <tt>#eql?</tt> and <tt>#==</tt> methods are
|
|
196
|
-
overriden to check if two Ruby objects wrap the same xmlnode. If they do,
|
|
197
|
-
then the methods return true. During the mark phase, each of these temporary
|
|
198
|
-
objects marks its owning document, thereby keeping the Ruby document object
|
|
199
|
-
alive and thus the xmldoc tree.
|
|
200
|
-
|
|
201
|
-
In the sweep phase of the garbage collector, or when a program ends,
|
|
202
|
-
there is no order to how Ruby objects are freed. In fact, the Ruby document
|
|
203
|
-
object is almost always freed before any Ruby objects that wrap child nodes.
|
|
204
|
-
However, this is ok because those Ruby objects do not have a free function
|
|
205
|
-
and are no longer in scope (since if they were the document would not be freed).
|
|
206
|
-
|
|
207
|
-
== License
|
|
208
|
-
See LICENSE for license information.
|
data/ext/libxml/extconf.h
DELETED
data/ext/libxml/ruby_xml_cbg.c
DELETED
|
@@ -1,85 +0,0 @@
|
|
|
1
|
-
#include "ruby_libxml.h"
|
|
2
|
-
#include <string.h>
|
|
3
|
-
#include <libxml/xmlIO.h>
|
|
4
|
-
|
|
5
|
-
/*
|
|
6
|
-
int xmlRegisterInputCallbacks (xmlInputMatchCallback matchFunc,
|
|
7
|
-
xmlInputOpenCallback openFunc,
|
|
8
|
-
xmlInputReadCallback readFunc,
|
|
9
|
-
xmlInputCloseCallback closeFunc);
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
int (*xmlInputMatchCallback) (char const *filename);
|
|
13
|
-
void* (*xmlInputOpenCallback) (char const *filename);
|
|
14
|
-
int (*xmlInputReadCallback) (void *context,
|
|
15
|
-
char *buffer,
|
|
16
|
-
int len);
|
|
17
|
-
int (*xmlInputCloseCallback) (void *context);
|
|
18
|
-
*/
|
|
19
|
-
|
|
20
|
-
typedef struct deb_doc_context
|
|
21
|
-
{
|
|
22
|
-
char *buffer;
|
|
23
|
-
char *bpos;
|
|
24
|
-
int remaining;
|
|
25
|
-
} deb_doc_context;
|
|
26
|
-
|
|
27
|
-
int deb_Match(char const *filename)
|
|
28
|
-
{
|
|
29
|
-
fprintf(stderr, "deb_Match: %s\n", filename);
|
|
30
|
-
if (!xmlStrncasecmp(BAD_CAST filename, BAD_CAST "deb://", 6))
|
|
31
|
-
{
|
|
32
|
-
return (1);
|
|
33
|
-
}
|
|
34
|
-
return (0);
|
|
35
|
-
}
|
|
36
|
-
|
|
37
|
-
void* deb_Open(char const *filename)
|
|
38
|
-
{
|
|
39
|
-
deb_doc_context *deb_doc;
|
|
40
|
-
VALUE res;
|
|
41
|
-
|
|
42
|
-
deb_doc = (deb_doc_context*) malloc(sizeof(deb_doc_context));
|
|
43
|
-
|
|
44
|
-
res = rb_funcall(rb_funcall(rb_mKernel, rb_intern("const_get"), 1,
|
|
45
|
-
rb_str_new2("DEBSystem")), rb_intern("document_query"), 1, rb_str_new2(filename));
|
|
46
|
-
deb_doc->buffer = strdup(StringValuePtr(res));
|
|
47
|
-
//deb_doc->buffer = strdup("<serepes>serepes</serepes>");
|
|
48
|
-
|
|
49
|
-
deb_doc->bpos = deb_doc->buffer;
|
|
50
|
-
deb_doc->remaining = (int)strlen(deb_doc->buffer);
|
|
51
|
-
return deb_doc;
|
|
52
|
-
}
|
|
53
|
-
|
|
54
|
-
int deb_Read(void *context, char *buffer, int len)
|
|
55
|
-
{
|
|
56
|
-
deb_doc_context *deb_doc;
|
|
57
|
-
int ret_len;
|
|
58
|
-
deb_doc = (deb_doc_context*) context;
|
|
59
|
-
|
|
60
|
-
if (len >= deb_doc->remaining)
|
|
61
|
-
{
|
|
62
|
-
ret_len = deb_doc->remaining;
|
|
63
|
-
}
|
|
64
|
-
else
|
|
65
|
-
{
|
|
66
|
-
ret_len = len;
|
|
67
|
-
}
|
|
68
|
-
deb_doc->remaining -= ret_len;
|
|
69
|
-
strncpy(buffer, deb_doc->bpos, ret_len);
|
|
70
|
-
deb_doc->bpos += ret_len;
|
|
71
|
-
|
|
72
|
-
return ret_len;
|
|
73
|
-
}
|
|
74
|
-
|
|
75
|
-
int deb_Close(void *context)
|
|
76
|
-
{
|
|
77
|
-
free(((deb_doc_context*) context)->buffer);
|
|
78
|
-
free(context);
|
|
79
|
-
return 1;
|
|
80
|
-
}
|
|
81
|
-
|
|
82
|
-
void deb_register_cbg(void)
|
|
83
|
-
{
|
|
84
|
-
xmlRegisterInputCallbacks(deb_Match, deb_Open, deb_Read, deb_Close);
|
|
85
|
-
}
|
data/lib/libxml/hpricot.rb
DELETED
|
@@ -1,78 +0,0 @@
|
|
|
1
|
-
# encoding: UTF-8
|
|
2
|
-
|
|
3
|
-
## Provide hpricot API for libxml. Provided by Michael Guterl,
|
|
4
|
-
## inspired by http://thebogles.com/blog/an-hpricot-style-interface-to-libxml
|
|
5
|
-
#
|
|
6
|
-
#class String
|
|
7
|
-
# def to_libxml_doc
|
|
8
|
-
# xp = XML::Parser.new
|
|
9
|
-
# xp.string = self
|
|
10
|
-
# xp.parse
|
|
11
|
-
# end
|
|
12
|
-
#end
|
|
13
|
-
#
|
|
14
|
-
#module LibXML
|
|
15
|
-
# module XML
|
|
16
|
-
# class Document
|
|
17
|
-
# alias :search :find
|
|
18
|
-
# end
|
|
19
|
-
#
|
|
20
|
-
# class Node
|
|
21
|
-
# # find the child node with the given xpath
|
|
22
|
-
# def at(xpath)
|
|
23
|
-
# self.find_first(xpath)
|
|
24
|
-
# end
|
|
25
|
-
#
|
|
26
|
-
# # find the array of child nodes matching the given xpath
|
|
27
|
-
# def search(xpath)
|
|
28
|
-
# results = self.find(xpath).to_a
|
|
29
|
-
# if block_given?
|
|
30
|
-
# results.each do |result|
|
|
31
|
-
# yield result
|
|
32
|
-
# end
|
|
33
|
-
# end
|
|
34
|
-
# return results
|
|
35
|
-
# end
|
|
36
|
-
#
|
|
37
|
-
# def /(xpath)
|
|
38
|
-
# search(xpath)
|
|
39
|
-
# end
|
|
40
|
-
#
|
|
41
|
-
# # return the inner contents of this node as a string
|
|
42
|
-
# def inner_xml
|
|
43
|
-
# child.to_s
|
|
44
|
-
# end
|
|
45
|
-
#
|
|
46
|
-
# # alias for inner_xml
|
|
47
|
-
# def inner_html
|
|
48
|
-
# inner_xml
|
|
49
|
-
# end
|
|
50
|
-
#
|
|
51
|
-
# # return this node and its contents as an xml string
|
|
52
|
-
# def to_xml
|
|
53
|
-
# self.to_s
|
|
54
|
-
# end
|
|
55
|
-
#
|
|
56
|
-
# # alias for path
|
|
57
|
-
# def xpath
|
|
58
|
-
# self.path
|
|
59
|
-
# end
|
|
60
|
-
#
|
|
61
|
-
# def find_with_default_ns(xpath_expr, namespace=nil)
|
|
62
|
-
# find_base(xpath_expr, namespace || default_namespaces)
|
|
63
|
-
# end
|
|
64
|
-
#
|
|
65
|
-
# def find_first_with_default_ns(xpath_expr, namespace=nil)
|
|
66
|
-
# find_first_base(xpath_expr, namespace || default_namespaces)
|
|
67
|
-
# end
|
|
68
|
-
#
|
|
69
|
-
## alias_method :find_base, :find unless method_defined?(:find_base)
|
|
70
|
-
## alias_method :find, :find_with_default_ns
|
|
71
|
-
## alias_method :find_first_base, :find_first unless method_defined?(:find_first_base)
|
|
72
|
-
## alias_method :find_first, :find_first_with_default_ns
|
|
73
|
-
## alias :child? :first?
|
|
74
|
-
## alias :children? :first?
|
|
75
|
-
## alias :child :first
|
|
76
|
-
# end
|
|
77
|
-
# end
|
|
78
|
-
#end
|
data/lib/libxml.rb
DELETED
data/lib/xml/libxml.rb
DELETED
data/lib/xml.rb
DELETED
|
@@ -1,14 +0,0 @@
|
|
|
1
|
-
# encoding: UTF-8
|
|
2
|
-
|
|
3
|
-
# This file loads libxml and adds the LibXML namespace
|
|
4
|
-
# to the toplevel for conveneience. The end result
|
|
5
|
-
# is to have XML:: universally exposed.
|
|
6
|
-
#
|
|
7
|
-
# It is recommend that you only load this file for libs
|
|
8
|
-
# that do not have their own namespace, eg. administrative
|
|
9
|
-
# scripts, personal programs, etc. For other applications
|
|
10
|
-
# require 'libxml' instead and include LibXML into your
|
|
11
|
-
# app/libs namespace.
|
|
12
|
-
|
|
13
|
-
require 'libxml'
|
|
14
|
-
include LibXML
|