nokogiri 1.10.7 → 1.16.0
Sign up to get free protection for your applications and to get access to all the features.
Potentially problematic release.
This version of nokogiri might be problematic. Click here for more details.
- checksums.yaml +4 -4
- data/Gemfile +42 -0
- data/LICENSE-DEPENDENCIES.md +1632 -1022
- data/LICENSE.md +1 -1
- data/README.md +188 -96
- data/bin/nokogiri +63 -50
- data/dependencies.yml +34 -66
- data/ext/nokogiri/depend +38 -358
- data/ext/nokogiri/extconf.rb +862 -421
- data/ext/nokogiri/gumbo.c +594 -0
- data/ext/nokogiri/html4_document.c +165 -0
- data/ext/nokogiri/html4_element_description.c +299 -0
- data/ext/nokogiri/html4_entity_lookup.c +37 -0
- data/ext/nokogiri/html4_sax_parser_context.c +108 -0
- data/ext/nokogiri/html4_sax_push_parser.c +95 -0
- data/ext/nokogiri/libxml2_backwards_compat.c +121 -0
- data/ext/nokogiri/nokogiri.c +251 -105
- data/ext/nokogiri/nokogiri.h +222 -90
- data/ext/nokogiri/test_global_handlers.c +40 -0
- data/ext/nokogiri/xml_attr.c +17 -17
- data/ext/nokogiri/xml_attribute_decl.c +22 -22
- data/ext/nokogiri/xml_cdata.c +39 -31
- data/ext/nokogiri/xml_comment.c +20 -27
- data/ext/nokogiri/xml_document.c +408 -243
- data/ext/nokogiri/xml_document_fragment.c +13 -17
- data/ext/nokogiri/xml_dtd.c +64 -58
- data/ext/nokogiri/xml_element_content.c +63 -55
- data/ext/nokogiri/xml_element_decl.c +31 -31
- data/ext/nokogiri/xml_encoding_handler.c +54 -21
- data/ext/nokogiri/xml_entity_decl.c +37 -35
- data/ext/nokogiri/xml_entity_reference.c +17 -19
- data/ext/nokogiri/xml_namespace.c +131 -61
- data/ext/nokogiri/xml_node.c +1343 -674
- data/ext/nokogiri/xml_node_set.c +246 -216
- data/ext/nokogiri/xml_processing_instruction.c +18 -20
- data/ext/nokogiri/xml_reader.c +305 -213
- data/ext/nokogiri/xml_relax_ng.c +87 -78
- data/ext/nokogiri/xml_sax_parser.c +149 -124
- data/ext/nokogiri/xml_sax_parser_context.c +149 -103
- data/ext/nokogiri/xml_sax_push_parser.c +65 -37
- data/ext/nokogiri/xml_schema.c +138 -82
- data/ext/nokogiri/xml_syntax_error.c +42 -21
- data/ext/nokogiri/xml_text.c +35 -26
- data/ext/nokogiri/xml_xpath_context.c +363 -178
- data/ext/nokogiri/xslt_stylesheet.c +335 -189
- data/gumbo-parser/CHANGES.md +63 -0
- data/gumbo-parser/Makefile +126 -0
- data/gumbo-parser/THANKS +27 -0
- data/gumbo-parser/src/Makefile +34 -0
- data/gumbo-parser/src/README.md +41 -0
- data/gumbo-parser/src/ascii.c +75 -0
- data/gumbo-parser/src/ascii.h +115 -0
- data/gumbo-parser/src/attribute.c +42 -0
- data/gumbo-parser/src/attribute.h +17 -0
- data/gumbo-parser/src/char_ref.c +22225 -0
- data/gumbo-parser/src/char_ref.h +29 -0
- data/gumbo-parser/src/char_ref.rl +2154 -0
- data/gumbo-parser/src/error.c +630 -0
- data/gumbo-parser/src/error.h +148 -0
- data/gumbo-parser/src/foreign_attrs.c +103 -0
- data/gumbo-parser/src/foreign_attrs.gperf +27 -0
- data/gumbo-parser/src/insertion_mode.h +33 -0
- data/gumbo-parser/src/macros.h +91 -0
- data/gumbo-parser/src/nokogiri_gumbo.h +944 -0
- data/gumbo-parser/src/parser.c +4891 -0
- data/gumbo-parser/src/parser.h +41 -0
- data/gumbo-parser/src/replacement.h +33 -0
- data/gumbo-parser/src/string_buffer.c +103 -0
- data/gumbo-parser/src/string_buffer.h +68 -0
- data/gumbo-parser/src/string_piece.c +48 -0
- data/gumbo-parser/src/svg_attrs.c +174 -0
- data/gumbo-parser/src/svg_attrs.gperf +77 -0
- data/gumbo-parser/src/svg_tags.c +137 -0
- data/gumbo-parser/src/svg_tags.gperf +55 -0
- data/gumbo-parser/src/tag.c +223 -0
- data/gumbo-parser/src/tag_lookup.c +382 -0
- data/gumbo-parser/src/tag_lookup.gperf +170 -0
- data/gumbo-parser/src/tag_lookup.h +13 -0
- data/gumbo-parser/src/token_buffer.c +79 -0
- data/gumbo-parser/src/token_buffer.h +71 -0
- data/gumbo-parser/src/token_type.h +17 -0
- data/gumbo-parser/src/tokenizer.c +3464 -0
- data/gumbo-parser/src/tokenizer.h +112 -0
- data/gumbo-parser/src/tokenizer_states.h +339 -0
- data/gumbo-parser/src/utf8.c +245 -0
- data/gumbo-parser/src/utf8.h +164 -0
- data/gumbo-parser/src/util.c +66 -0
- data/gumbo-parser/src/util.h +34 -0
- data/gumbo-parser/src/vector.c +111 -0
- data/gumbo-parser/src/vector.h +45 -0
- data/lib/nokogiri/class_resolver.rb +67 -0
- data/lib/nokogiri/css/node.rb +10 -8
- data/lib/nokogiri/css/parser.rb +397 -377
- data/lib/nokogiri/css/parser.y +250 -245
- data/lib/nokogiri/css/parser_extras.rb +54 -49
- data/lib/nokogiri/css/syntax_error.rb +3 -1
- data/lib/nokogiri/css/tokenizer.rb +5 -3
- data/lib/nokogiri/css/tokenizer.rex +3 -2
- data/lib/nokogiri/css/xpath_visitor.rb +205 -96
- data/lib/nokogiri/css.rb +56 -17
- data/lib/nokogiri/decorators/slop.rb +9 -7
- data/lib/nokogiri/encoding_handler.rb +57 -0
- data/lib/nokogiri/extension.rb +32 -0
- data/lib/nokogiri/gumbo.rb +15 -0
- data/lib/nokogiri/html.rb +38 -27
- data/lib/nokogiri/{html → html4}/builder.rb +4 -2
- data/lib/nokogiri/html4/document.rb +214 -0
- data/lib/nokogiri/html4/document_fragment.rb +54 -0
- data/lib/nokogiri/{html → html4}/element_description.rb +3 -1
- data/lib/nokogiri/html4/element_description_defaults.rb +2040 -0
- data/lib/nokogiri/html4/encoding_reader.rb +121 -0
- data/lib/nokogiri/{html → html4}/entity_lookup.rb +4 -2
- data/lib/nokogiri/{html → html4}/sax/parser.rb +17 -16
- data/lib/nokogiri/html4/sax/parser_context.rb +20 -0
- data/lib/nokogiri/{html → html4}/sax/push_parser.rb +12 -11
- data/lib/nokogiri/html4.rb +47 -0
- data/lib/nokogiri/html5/document.rb +168 -0
- data/lib/nokogiri/html5/document_fragment.rb +90 -0
- data/lib/nokogiri/html5/node.rb +103 -0
- data/lib/nokogiri/html5.rb +326 -0
- data/lib/nokogiri/jruby/dependencies.rb +3 -0
- data/lib/nokogiri/jruby/nokogiri_jars.rb +43 -0
- data/lib/nokogiri/syntax_error.rb +2 -0
- data/lib/nokogiri/version/constant.rb +6 -0
- data/lib/nokogiri/version/info.rb +224 -0
- data/lib/nokogiri/version.rb +3 -108
- data/lib/nokogiri/xml/attr.rb +55 -3
- data/lib/nokogiri/xml/attribute_decl.rb +6 -2
- data/lib/nokogiri/xml/builder.rb +75 -34
- data/lib/nokogiri/xml/cdata.rb +3 -1
- data/lib/nokogiri/xml/character_data.rb +2 -0
- data/lib/nokogiri/xml/document.rb +312 -127
- data/lib/nokogiri/xml/document_fragment.rb +93 -48
- data/lib/nokogiri/xml/dtd.rb +4 -2
- data/lib/nokogiri/xml/element_content.rb +12 -2
- data/lib/nokogiri/xml/element_decl.rb +6 -2
- data/lib/nokogiri/xml/entity_decl.rb +7 -3
- data/lib/nokogiri/xml/entity_reference.rb +2 -0
- data/lib/nokogiri/xml/namespace.rb +44 -0
- data/lib/nokogiri/xml/node/save_options.rb +23 -8
- data/lib/nokogiri/xml/node.rb +1096 -419
- data/lib/nokogiri/xml/node_set.rb +137 -61
- data/lib/nokogiri/xml/notation.rb +13 -0
- data/lib/nokogiri/xml/parse_options.rb +145 -52
- data/lib/nokogiri/xml/pp/character_data.rb +9 -6
- data/lib/nokogiri/xml/pp/node.rb +42 -30
- data/lib/nokogiri/xml/pp.rb +4 -2
- data/lib/nokogiri/xml/processing_instruction.rb +4 -1
- data/lib/nokogiri/xml/reader.rb +21 -28
- data/lib/nokogiri/xml/relax_ng.rb +8 -2
- data/lib/nokogiri/xml/sax/document.rb +45 -49
- data/lib/nokogiri/xml/sax/parser.rb +39 -36
- data/lib/nokogiri/xml/sax/parser_context.rb +8 -3
- data/lib/nokogiri/xml/sax/push_parser.rb +6 -5
- data/lib/nokogiri/xml/sax.rb +6 -4
- data/lib/nokogiri/xml/schema.rb +19 -9
- data/lib/nokogiri/xml/searchable.rb +120 -72
- data/lib/nokogiri/xml/syntax_error.rb +7 -5
- data/lib/nokogiri/xml/text.rb +2 -0
- data/lib/nokogiri/xml/xpath/syntax_error.rb +4 -2
- data/lib/nokogiri/xml/xpath.rb +15 -4
- data/lib/nokogiri/xml/xpath_context.rb +3 -3
- data/lib/nokogiri/xml.rb +39 -38
- data/lib/nokogiri/xslt/stylesheet.rb +3 -1
- data/lib/nokogiri/xslt.rb +101 -22
- data/lib/nokogiri.rb +59 -75
- data/lib/xsd/xmlparser/nokogiri.rb +29 -25
- data/patches/libxml2/{0004-libxml2.la-is-in-top_builddir.patch → 0003-libxml2.la-is-in-top_builddir.patch} +1 -1
- data/patches/libxml2/0009-allow-wildcard-namespaces.patch +77 -0
- data/patches/libxml2/0010-update-config.guess-and-config.sub-for-libxml2.patch +224 -0
- data/patches/libxml2/0011-rip-out-libxml2-s-libc_single_threaded-support.patch +30 -0
- data/patches/libxslt/0001-update-config.guess-and-config.sub-for-libxslt.patch +224 -0
- data/ports/archives/libxml2-2.12.3.tar.xz +0 -0
- data/ports/archives/libxslt-1.1.39.tar.xz +0 -0
- metadata +121 -291
- data/ext/nokogiri/html_document.c +0 -170
- data/ext/nokogiri/html_document.h +0 -10
- data/ext/nokogiri/html_element_description.c +0 -279
- data/ext/nokogiri/html_element_description.h +0 -10
- data/ext/nokogiri/html_entity_lookup.c +0 -32
- data/ext/nokogiri/html_entity_lookup.h +0 -8
- data/ext/nokogiri/html_sax_parser_context.c +0 -116
- data/ext/nokogiri/html_sax_parser_context.h +0 -11
- data/ext/nokogiri/html_sax_push_parser.c +0 -87
- data/ext/nokogiri/html_sax_push_parser.h +0 -9
- data/ext/nokogiri/xml_attr.h +0 -9
- data/ext/nokogiri/xml_attribute_decl.h +0 -9
- data/ext/nokogiri/xml_cdata.h +0 -9
- data/ext/nokogiri/xml_comment.h +0 -9
- data/ext/nokogiri/xml_document.h +0 -23
- data/ext/nokogiri/xml_document_fragment.h +0 -10
- data/ext/nokogiri/xml_dtd.h +0 -10
- data/ext/nokogiri/xml_element_content.h +0 -10
- data/ext/nokogiri/xml_element_decl.h +0 -9
- data/ext/nokogiri/xml_encoding_handler.h +0 -8
- data/ext/nokogiri/xml_entity_decl.h +0 -10
- data/ext/nokogiri/xml_entity_reference.h +0 -9
- data/ext/nokogiri/xml_io.c +0 -61
- data/ext/nokogiri/xml_io.h +0 -11
- data/ext/nokogiri/xml_libxml2_hacks.c +0 -112
- data/ext/nokogiri/xml_libxml2_hacks.h +0 -12
- data/ext/nokogiri/xml_namespace.h +0 -14
- data/ext/nokogiri/xml_node.h +0 -13
- data/ext/nokogiri/xml_node_set.h +0 -12
- data/ext/nokogiri/xml_processing_instruction.h +0 -9
- data/ext/nokogiri/xml_reader.h +0 -10
- data/ext/nokogiri/xml_relax_ng.h +0 -9
- data/ext/nokogiri/xml_sax_parser.h +0 -39
- data/ext/nokogiri/xml_sax_parser_context.h +0 -10
- data/ext/nokogiri/xml_sax_push_parser.h +0 -9
- data/ext/nokogiri/xml_schema.h +0 -9
- data/ext/nokogiri/xml_syntax_error.h +0 -13
- data/ext/nokogiri/xml_text.h +0 -9
- data/ext/nokogiri/xml_xpath_context.h +0 -10
- data/ext/nokogiri/xslt_stylesheet.h +0 -14
- data/lib/nokogiri/html/document.rb +0 -335
- data/lib/nokogiri/html/document_fragment.rb +0 -49
- data/lib/nokogiri/html/element_description_defaults.rb +0 -671
- data/lib/nokogiri/html/sax/parser_context.rb +0 -16
- data/patches/libxml2/0001-Revert-Do-not-URI-escape-in-server-side-includes.patch +0 -78
- data/ports/archives/libxml2-2.9.10.tar.gz +0 -0
- data/ports/archives/libxslt-1.1.34.tar.gz +0 -0
- /data/patches/libxml2/{0002-Remove-script-macro-support.patch → 0001-Remove-script-macro-support.patch} +0 -0
- /data/patches/libxml2/{0003-Update-entities-to-remove-handling-of-ssi.patch → 0002-Update-entities-to-remove-handling-of-ssi.patch} +0 -0
data/lib/nokogiri/xml/node.rb
CHANGED
@@ -1,105 +1,130 @@
|
|
1
|
-
# encoding:
|
2
|
-
|
3
|
-
|
1
|
+
# encoding: utf-8
|
2
|
+
# frozen_string_literal: true
|
3
|
+
|
4
|
+
require "stringio"
|
4
5
|
|
5
6
|
module Nokogiri
|
6
7
|
module XML
|
7
|
-
|
8
|
-
#
|
9
|
-
#
|
10
|
-
#
|
8
|
+
# Nokogiri::XML::Node is the primary API you'll use to interact with your Document.
|
9
|
+
#
|
10
|
+
# == Attributes
|
11
|
+
#
|
12
|
+
# A Nokogiri::XML::Node may be treated similarly to a hash with regard to attributes. For
|
13
|
+
# example:
|
14
|
+
#
|
15
|
+
# node = Nokogiri::XML::DocumentFragment.parse("<a href='#foo' id='link'>link</a>").at_css("a")
|
16
|
+
# node.to_html # => "<a href=\"#foo\" id=\"link\">link</a>"
|
17
|
+
# node['href'] # => "#foo"
|
18
|
+
# node.keys # => ["href", "id"]
|
19
|
+
# node.values # => ["#foo", "link"]
|
20
|
+
# node['class'] = 'green' # => "green"
|
21
|
+
# node.to_html # => "<a href=\"#foo\" id=\"link\" class=\"green\">link</a>"
|
22
|
+
#
|
23
|
+
# See the method group entitled Node@Working+With+Node+Attributes for the full set of methods.
|
24
|
+
#
|
25
|
+
# == Navigation
|
26
|
+
#
|
27
|
+
# Nokogiri::XML::Node also has methods that let you move around your tree:
|
11
28
|
#
|
12
|
-
#
|
13
|
-
#
|
14
|
-
# irb(main):005:0> node['href']
|
15
|
-
# => "#foo"
|
16
|
-
# irb(main):006:0> node.keys
|
17
|
-
# => ["href", "id"]
|
18
|
-
# irb(main):007:0> node.values
|
19
|
-
# => ["#foo", "link"]
|
20
|
-
# irb(main):008:0> node['class'] = 'green'
|
21
|
-
# => "green"
|
22
|
-
# irb(main):009:0> node
|
23
|
-
# => <a href="#foo" id="link" class="green">link</a>
|
24
|
-
# irb(main):010:0>
|
29
|
+
# [#parent, #children, #next, #previous]
|
30
|
+
# Navigate up, down, or through siblings.
|
25
31
|
#
|
26
|
-
# See
|
32
|
+
# See the method group entitled Node@Traversing+Document+Structure for the full set of methods.
|
27
33
|
#
|
28
|
-
#
|
29
|
-
# tree. For navigating your tree, see:
|
34
|
+
# == Serialization
|
30
35
|
#
|
31
|
-
#
|
32
|
-
#
|
33
|
-
# * Nokogiri::XML::Node#next
|
34
|
-
# * Nokogiri::XML::Node#previous
|
36
|
+
# When printing or otherwise emitting a document or a node (and its subtree), there are a few
|
37
|
+
# methods you might want to use:
|
35
38
|
#
|
39
|
+
# [#content, #text, #inner_text, #to_str]
|
40
|
+
# These methods will all **emit plaintext**,
|
41
|
+
# meaning that entities will be replaced (e.g., +<+ will be replaced with +<+), meaning
|
42
|
+
# that any sanitizing will likely be un-done in the output.
|
36
43
|
#
|
37
|
-
#
|
38
|
-
#
|
44
|
+
# [#to_s, #to_xml, #to_html, #inner_html]
|
45
|
+
# These methods will all **emit properly-escaped markup**, meaning that it's suitable for
|
46
|
+
# consumption by browsers, parsers, etc.
|
39
47
|
#
|
40
|
-
#
|
48
|
+
# See the method group entitled Node@Serialization+and+Generating+Output for the full set of methods.
|
41
49
|
#
|
42
|
-
#
|
43
|
-
# document, meaning that entities will be replaced (e.g., "<"
|
44
|
-
# will be replaced with "<"), meaning that any sanitizing will
|
45
|
-
# likely be un-done in the output.
|
50
|
+
# == Searching
|
46
51
|
#
|
47
|
-
#
|
52
|
+
# You may search this node's subtree using methods like #xpath and #css.
|
48
53
|
#
|
49
|
-
#
|
50
|
-
# that it's suitable for consumption by browsers, parsers, etc.
|
54
|
+
# See the method group entitled Node@Searching+via+XPath+or+CSS+Queries for the full set of methods.
|
51
55
|
#
|
52
|
-
# You may search this node's subtree using Searchable#xpath and Searchable#css
|
53
56
|
class Node
|
54
57
|
include Nokogiri::XML::PP::Node
|
55
58
|
include Nokogiri::XML::Searchable
|
59
|
+
include Nokogiri::ClassResolver
|
56
60
|
include Enumerable
|
57
61
|
|
58
62
|
# Element node type, see Nokogiri::XML::Node#element?
|
59
|
-
ELEMENT_NODE =
|
63
|
+
ELEMENT_NODE = 1
|
60
64
|
# Attribute node type
|
61
|
-
ATTRIBUTE_NODE =
|
65
|
+
ATTRIBUTE_NODE = 2
|
62
66
|
# Text node type, see Nokogiri::XML::Node#text?
|
63
|
-
TEXT_NODE =
|
67
|
+
TEXT_NODE = 3
|
64
68
|
# CDATA node type, see Nokogiri::XML::Node#cdata?
|
65
69
|
CDATA_SECTION_NODE = 4
|
66
70
|
# Entity reference node type
|
67
|
-
ENTITY_REF_NODE =
|
71
|
+
ENTITY_REF_NODE = 5
|
68
72
|
# Entity node type
|
69
|
-
ENTITY_NODE =
|
73
|
+
ENTITY_NODE = 6
|
70
74
|
# PI node type
|
71
|
-
PI_NODE =
|
75
|
+
PI_NODE = 7
|
72
76
|
# Comment node type, see Nokogiri::XML::Node#comment?
|
73
|
-
COMMENT_NODE =
|
77
|
+
COMMENT_NODE = 8
|
74
78
|
# Document node type, see Nokogiri::XML::Node#xml?
|
75
|
-
DOCUMENT_NODE =
|
79
|
+
DOCUMENT_NODE = 9
|
76
80
|
# Document type node type
|
77
81
|
DOCUMENT_TYPE_NODE = 10
|
78
82
|
# Document fragment node type
|
79
83
|
DOCUMENT_FRAG_NODE = 11
|
80
84
|
# Notation node type
|
81
|
-
NOTATION_NODE =
|
85
|
+
NOTATION_NODE = 12
|
82
86
|
# HTML document node type, see Nokogiri::XML::Node#html?
|
83
87
|
HTML_DOCUMENT_NODE = 13
|
84
88
|
# DTD node type
|
85
|
-
DTD_NODE =
|
89
|
+
DTD_NODE = 14
|
86
90
|
# Element declaration type
|
87
|
-
ELEMENT_DECL =
|
91
|
+
ELEMENT_DECL = 15
|
88
92
|
# Attribute declaration type
|
89
|
-
ATTRIBUTE_DECL =
|
93
|
+
ATTRIBUTE_DECL = 16
|
90
94
|
# Entity declaration type
|
91
|
-
ENTITY_DECL =
|
95
|
+
ENTITY_DECL = 17
|
92
96
|
# Namespace declaration type
|
93
|
-
NAMESPACE_DECL =
|
97
|
+
NAMESPACE_DECL = 18
|
94
98
|
# XInclude start type
|
95
|
-
XINCLUDE_START =
|
99
|
+
XINCLUDE_START = 19
|
96
100
|
# XInclude end type
|
97
|
-
XINCLUDE_END =
|
101
|
+
XINCLUDE_END = 20
|
98
102
|
# DOCB document node type
|
99
103
|
DOCB_DOCUMENT_NODE = 21
|
100
104
|
|
101
|
-
|
102
|
-
|
105
|
+
#
|
106
|
+
# :call-seq:
|
107
|
+
# new(name, document) -> Nokogiri::XML::Node
|
108
|
+
# new(name, document) { |node| ... } -> Nokogiri::XML::Node
|
109
|
+
#
|
110
|
+
# Create a new node with +name+ that belongs to +document+.
|
111
|
+
#
|
112
|
+
# If you intend to add a node to a document tree, it's likely that you will prefer one of the
|
113
|
+
# Nokogiri::XML::Node methods like #add_child, #add_next_sibling, #replace, etc. which will
|
114
|
+
# both create an element (or subtree) and place it in the document tree.
|
115
|
+
#
|
116
|
+
# Another alternative, if you are concerned about performance, is
|
117
|
+
# Nokogiri::XML::Document#create_element which accepts additional arguments for contents or
|
118
|
+
# attributes but (like this method) avoids parsing markup.
|
119
|
+
#
|
120
|
+
# [Parameters]
|
121
|
+
# - +name+ (String)
|
122
|
+
# - +document+ (Nokogiri::XML::Document) The document to which the the returned node will belong.
|
123
|
+
# [Yields] Nokogiri::XML::Node
|
124
|
+
# [Returns] Nokogiri::XML::Node
|
125
|
+
#
|
126
|
+
def initialize(name, document)
|
127
|
+
# This is intentionally empty, and sets the method signature for subclasses.
|
103
128
|
end
|
104
129
|
|
105
130
|
###
|
@@ -108,238 +133,483 @@ module Nokogiri
|
|
108
133
|
document.decorate(self)
|
109
134
|
end
|
110
135
|
|
111
|
-
|
112
|
-
# Search this node's immediate children using CSS selector +selector+
|
113
|
-
def > selector
|
114
|
-
ns = document.root.namespaces
|
115
|
-
xpath CSS.xpath_for(selector, :prefix => "./", :ns => ns).first
|
116
|
-
end
|
117
|
-
|
118
|
-
###
|
119
|
-
# Get the attribute value for the attribute +name+
|
120
|
-
def [] name
|
121
|
-
get(name.to_s)
|
122
|
-
end
|
123
|
-
|
124
|
-
###
|
125
|
-
# Set the attribute value for the attribute +name+ to +value+
|
126
|
-
def []= name, value
|
127
|
-
set name.to_s, value.to_s
|
128
|
-
end
|
136
|
+
# :section: Manipulating Document Structure
|
129
137
|
|
130
138
|
###
|
131
139
|
# Add +node_or_tags+ as a child of this Node.
|
132
|
-
# +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a string containing markup.
|
133
140
|
#
|
134
|
-
#
|
141
|
+
# +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a String
|
142
|
+
# containing markup.
|
143
|
+
#
|
144
|
+
# Returns the reparented node (if +node_or_tags+ is a Node), or NodeSet (if +node_or_tags+ is
|
145
|
+
# a DocumentFragment, NodeSet, or String).
|
135
146
|
#
|
136
147
|
# Also see related method +<<+.
|
137
|
-
def add_child
|
148
|
+
def add_child(node_or_tags)
|
138
149
|
node_or_tags = coerce(node_or_tags)
|
139
150
|
if node_or_tags.is_a?(XML::NodeSet)
|
140
|
-
node_or_tags.each { |n| add_child_node_and_reparent_attrs
|
151
|
+
node_or_tags.each { |n| add_child_node_and_reparent_attrs(n) }
|
141
152
|
else
|
142
|
-
add_child_node_and_reparent_attrs
|
153
|
+
add_child_node_and_reparent_attrs(node_or_tags)
|
143
154
|
end
|
144
155
|
node_or_tags
|
145
156
|
end
|
146
157
|
|
147
158
|
###
|
148
159
|
# Add +node_or_tags+ as the first child of this Node.
|
149
|
-
# +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a string containing markup.
|
150
160
|
#
|
151
|
-
#
|
161
|
+
# +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a String
|
162
|
+
# containing markup.
|
163
|
+
#
|
164
|
+
# Returns the reparented node (if +node_or_tags+ is a Node), or NodeSet (if +node_or_tags+ is
|
165
|
+
# a DocumentFragment, NodeSet, or String).
|
152
166
|
#
|
153
167
|
# Also see related method +add_child+.
|
154
|
-
def prepend_child
|
155
|
-
if first = children.first
|
168
|
+
def prepend_child(node_or_tags)
|
169
|
+
if (first = children.first)
|
156
170
|
# Mimic the error add_child would raise.
|
157
|
-
raise
|
171
|
+
raise "Document already has a root node" if document? && !(node_or_tags.comment? || node_or_tags.processing_instruction?)
|
172
|
+
|
158
173
|
first.__send__(:add_sibling, :previous, node_or_tags)
|
159
174
|
else
|
160
175
|
add_child(node_or_tags)
|
161
176
|
end
|
162
177
|
end
|
163
178
|
|
164
|
-
|
165
|
-
|
166
|
-
#
|
179
|
+
# :call-seq:
|
180
|
+
# wrap(markup) -> self
|
181
|
+
# wrap(node) -> self
|
167
182
|
#
|
168
|
-
#
|
169
|
-
|
170
|
-
|
171
|
-
|
183
|
+
# Wrap this Node with the node parsed from +markup+ or a dup of the +node+.
|
184
|
+
#
|
185
|
+
# [Parameters]
|
186
|
+
# - *markup* (String)
|
187
|
+
# Markup that is parsed and used as the wrapper. This node's parent, if it exists, is used
|
188
|
+
# as the context node for parsing; otherwise the associated document is used. If the parsed
|
189
|
+
# fragment has multiple roots, the first root node is used as the wrapper.
|
190
|
+
# - *node* (Nokogiri::XML::Node)
|
191
|
+
# An element that is `#dup`ed and used as the wrapper.
|
192
|
+
#
|
193
|
+
# [Returns] +self+, to support chaining.
|
194
|
+
#
|
195
|
+
# Also see NodeSet#wrap
|
196
|
+
#
|
197
|
+
# *Example* with a +String+ argument:
|
198
|
+
#
|
199
|
+
# doc = Nokogiri::HTML5(<<~HTML)
|
200
|
+
# <html><body>
|
201
|
+
# <a>asdf</a>
|
202
|
+
# </body></html>
|
203
|
+
# HTML
|
204
|
+
# doc.at_css("a").wrap("<div></div>")
|
205
|
+
# doc.to_html
|
206
|
+
# # => <html><head></head><body>
|
207
|
+
# # <div><a>asdf</a></div>
|
208
|
+
# # </body></html>
|
209
|
+
#
|
210
|
+
# *Example* with a +Node+ argument:
|
211
|
+
#
|
212
|
+
# doc = Nokogiri::HTML5(<<~HTML)
|
213
|
+
# <html><body>
|
214
|
+
# <a>asdf</a>
|
215
|
+
# </body></html>
|
216
|
+
# HTML
|
217
|
+
# doc.at_css("a").wrap(doc.create_element("div"))
|
218
|
+
# doc.to_html
|
219
|
+
# # <html><head></head><body>
|
220
|
+
# # <div><a>asdf</a></div>
|
221
|
+
# # </body></html>
|
222
|
+
#
|
223
|
+
def wrap(node_or_tags)
|
224
|
+
case node_or_tags
|
225
|
+
when String
|
226
|
+
context_node = parent || document
|
227
|
+
new_parent = context_node.coerce(node_or_tags).first
|
228
|
+
if new_parent.nil?
|
229
|
+
raise "Failed to parse '#{node_or_tags}' in the context of a '#{context_node.name}' element"
|
230
|
+
end
|
231
|
+
when XML::Node
|
232
|
+
new_parent = node_or_tags.dup
|
233
|
+
else
|
234
|
+
raise ArgumentError, "Requires a String or Node argument, and cannot accept a #{node_or_tags.class}"
|
235
|
+
end
|
236
|
+
|
237
|
+
if parent
|
238
|
+
add_next_sibling(new_parent)
|
239
|
+
else
|
240
|
+
new_parent.unlink
|
241
|
+
end
|
172
242
|
new_parent.add_child(self)
|
243
|
+
|
173
244
|
self
|
174
245
|
end
|
175
246
|
|
176
247
|
###
|
177
248
|
# Add +node_or_tags+ as a child of this Node.
|
178
|
-
# +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a string containing markup.
|
179
249
|
#
|
180
|
-
#
|
250
|
+
# +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a String
|
251
|
+
# containing markup.
|
252
|
+
#
|
253
|
+
# Returns +self+, to support chaining of calls (e.g., root << child1 << child2)
|
181
254
|
#
|
182
255
|
# Also see related method +add_child+.
|
183
|
-
def <<
|
184
|
-
add_child
|
256
|
+
def <<(node_or_tags)
|
257
|
+
add_child(node_or_tags)
|
185
258
|
self
|
186
259
|
end
|
187
260
|
|
188
261
|
###
|
189
262
|
# Insert +node_or_tags+ before this Node (as a sibling).
|
190
|
-
# +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a string containing markup.
|
191
263
|
#
|
192
|
-
#
|
264
|
+
# +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a String
|
265
|
+
# containing markup.
|
266
|
+
#
|
267
|
+
# Returns the reparented node (if +node_or_tags+ is a Node), or NodeSet (if +node_or_tags+ is
|
268
|
+
# a DocumentFragment, NodeSet, or String).
|
193
269
|
#
|
194
270
|
# Also see related method +before+.
|
195
|
-
def add_previous_sibling
|
196
|
-
raise ArgumentError
|
271
|
+
def add_previous_sibling(node_or_tags)
|
272
|
+
raise ArgumentError,
|
273
|
+
"A document may not have multiple root nodes." if parent&.document? && !(node_or_tags.comment? || node_or_tags.processing_instruction?)
|
197
274
|
|
198
|
-
add_sibling
|
275
|
+
add_sibling(:previous, node_or_tags)
|
199
276
|
end
|
200
277
|
|
201
278
|
###
|
202
279
|
# Insert +node_or_tags+ after this Node (as a sibling).
|
203
|
-
# +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a string containing markup.
|
204
280
|
#
|
205
|
-
#
|
281
|
+
# +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a String
|
282
|
+
# containing markup.
|
283
|
+
#
|
284
|
+
# Returns the reparented node (if +node_or_tags+ is a Node), or NodeSet (if +node_or_tags+ is
|
285
|
+
# a DocumentFragment, NodeSet, or String).
|
206
286
|
#
|
207
287
|
# Also see related method +after+.
|
208
|
-
def add_next_sibling
|
209
|
-
raise ArgumentError
|
288
|
+
def add_next_sibling(node_or_tags)
|
289
|
+
raise ArgumentError,
|
290
|
+
"A document may not have multiple root nodes." if parent&.document? && !(node_or_tags.comment? || node_or_tags.processing_instruction?)
|
210
291
|
|
211
|
-
add_sibling
|
292
|
+
add_sibling(:next, node_or_tags)
|
212
293
|
end
|
213
294
|
|
214
295
|
####
|
215
296
|
# Insert +node_or_tags+ before this node (as a sibling).
|
216
|
-
# +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a string containing markup.
|
217
297
|
#
|
218
|
-
#
|
298
|
+
# +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a String
|
299
|
+
# containing markup.
|
300
|
+
#
|
301
|
+
# Returns +self+, to support chaining of calls.
|
219
302
|
#
|
220
303
|
# Also see related method +add_previous_sibling+.
|
221
|
-
def before
|
222
|
-
add_previous_sibling
|
304
|
+
def before(node_or_tags)
|
305
|
+
add_previous_sibling(node_or_tags)
|
223
306
|
self
|
224
307
|
end
|
225
308
|
|
226
309
|
####
|
227
310
|
# Insert +node_or_tags+ after this node (as a sibling).
|
228
|
-
# +node_or_tags+ can be a Nokogiri::XML::Node, a Nokogiri::XML::DocumentFragment, or a string containing markup.
|
229
311
|
#
|
230
|
-
#
|
312
|
+
# +node_or_tags+ can be a Nokogiri::XML::Node, a Nokogiri::XML::DocumentFragment, or a String
|
313
|
+
# containing markup.
|
314
|
+
#
|
315
|
+
# Returns +self+, to support chaining of calls.
|
231
316
|
#
|
232
317
|
# Also see related method +add_next_sibling+.
|
233
|
-
def after
|
234
|
-
add_next_sibling
|
318
|
+
def after(node_or_tags)
|
319
|
+
add_next_sibling(node_or_tags)
|
235
320
|
self
|
236
321
|
end
|
237
322
|
|
238
323
|
####
|
239
|
-
# Set the
|
240
|
-
# +node_or_tags+ can be a Nokogiri::XML::Node, a Nokogiri::XML::DocumentFragment, or a string containing markup.
|
324
|
+
# Set the content for this Node to +node_or_tags+.
|
241
325
|
#
|
242
|
-
#
|
326
|
+
# +node_or_tags+ can be a Nokogiri::XML::Node, a Nokogiri::XML::DocumentFragment, or a String
|
327
|
+
# containing markup.
|
328
|
+
#
|
329
|
+
# ⚠ Please note that despite the name, this method will *not* always parse a String argument
|
330
|
+
# as HTML. A String argument will be parsed with the +DocumentFragment+ parser related to this
|
331
|
+
# node's document.
|
332
|
+
#
|
333
|
+
# For example, if the document is an HTML4::Document then the string will be parsed as HTML4
|
334
|
+
# using HTML4::DocumentFragment; but if the document is an XML::Document then it will
|
335
|
+
# parse the string as XML using XML::DocumentFragment.
|
243
336
|
#
|
244
337
|
# Also see related method +children=+
|
245
|
-
def inner_html=
|
338
|
+
def inner_html=(node_or_tags)
|
246
339
|
self.children = node_or_tags
|
247
|
-
self
|
248
340
|
end
|
249
341
|
|
250
342
|
####
|
251
|
-
# Set the
|
252
|
-
# +node_or_tags+ can be a Nokogiri::XML::Node, a Nokogiri::XML::DocumentFragment, or a string containing markup.
|
343
|
+
# Set the content for this Node +node_or_tags+
|
253
344
|
#
|
254
|
-
#
|
345
|
+
# +node_or_tags+ can be a Nokogiri::XML::Node, a Nokogiri::XML::DocumentFragment, or a String
|
346
|
+
# containing markup.
|
255
347
|
#
|
256
348
|
# Also see related method +inner_html=+
|
257
|
-
def children=
|
349
|
+
def children=(node_or_tags)
|
258
350
|
node_or_tags = coerce(node_or_tags)
|
259
351
|
children.unlink
|
260
352
|
if node_or_tags.is_a?(XML::NodeSet)
|
261
|
-
node_or_tags.each { |n| add_child_node_and_reparent_attrs
|
353
|
+
node_or_tags.each { |n| add_child_node_and_reparent_attrs(n) }
|
262
354
|
else
|
263
|
-
add_child_node_and_reparent_attrs
|
355
|
+
add_child_node_and_reparent_attrs(node_or_tags)
|
264
356
|
end
|
265
|
-
node_or_tags
|
266
357
|
end
|
267
358
|
|
268
359
|
####
|
269
360
|
# Replace this Node with +node_or_tags+.
|
270
|
-
# +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a string containing markup.
|
271
361
|
#
|
272
|
-
#
|
362
|
+
# +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a String
|
363
|
+
# containing markup.
|
364
|
+
#
|
365
|
+
# Returns the reparented node (if +node_or_tags+ is a Node), or NodeSet (if +node_or_tags+ is
|
366
|
+
# a DocumentFragment, NodeSet, or String).
|
273
367
|
#
|
274
368
|
# Also see related method +swap+.
|
275
|
-
def replace
|
369
|
+
def replace(node_or_tags)
|
370
|
+
raise("Cannot replace a node with no parent") unless parent
|
371
|
+
|
276
372
|
# We cannot replace a text node directly, otherwise libxml will return
|
277
373
|
# an internal error at parser.c:13031, I don't know exactly why
|
278
374
|
# libxml is trying to find a parent node that is an element or document
|
279
375
|
# so I can't tell if this is bug in libxml or not. issue #775.
|
280
376
|
if text?
|
281
|
-
replacee = Nokogiri::XML::Node.new
|
282
|
-
add_previous_sibling_node
|
377
|
+
replacee = Nokogiri::XML::Node.new("dummy", document)
|
378
|
+
add_previous_sibling_node(replacee)
|
283
379
|
unlink
|
284
|
-
return replacee.replace
|
380
|
+
return replacee.replace(node_or_tags)
|
285
381
|
end
|
286
382
|
|
287
|
-
node_or_tags = coerce(node_or_tags)
|
383
|
+
node_or_tags = parent.coerce(node_or_tags)
|
288
384
|
|
289
385
|
if node_or_tags.is_a?(XML::NodeSet)
|
290
|
-
node_or_tags.each { |n| add_previous_sibling
|
386
|
+
node_or_tags.each { |n| add_previous_sibling(n) }
|
291
387
|
unlink
|
292
388
|
else
|
293
|
-
replace_node
|
389
|
+
replace_node(node_or_tags)
|
294
390
|
end
|
295
391
|
node_or_tags
|
296
392
|
end
|
297
393
|
|
298
394
|
####
|
299
395
|
# Swap this Node for +node_or_tags+
|
300
|
-
#
|
396
|
+
#
|
397
|
+
# +node_or_tags+ can be a Nokogiri::XML::Node, a ::DocumentFragment, a ::NodeSet, or a String
|
398
|
+
# Containing markup.
|
301
399
|
#
|
302
400
|
# Returns self, to support chaining of calls.
|
303
401
|
#
|
304
402
|
# Also see related method +replace+.
|
305
|
-
def swap
|
306
|
-
replace
|
403
|
+
def swap(node_or_tags)
|
404
|
+
replace(node_or_tags)
|
307
405
|
self
|
308
406
|
end
|
309
407
|
|
310
|
-
alias :next :next_sibling
|
311
|
-
alias :previous :previous_sibling
|
312
|
-
|
313
|
-
# :stopdoc:
|
314
|
-
# HACK: This is to work around an RDoc bug
|
315
|
-
alias :next= :add_next_sibling
|
316
|
-
# :startdoc:
|
317
|
-
|
318
|
-
alias :previous= :add_previous_sibling
|
319
|
-
alias :remove :unlink
|
320
|
-
alias :get_attribute :[]
|
321
|
-
alias :attr :[]
|
322
|
-
alias :set_attribute :[]=
|
323
|
-
alias :text :content
|
324
|
-
alias :inner_text :content
|
325
|
-
alias :has_attribute? :key?
|
326
|
-
alias :name :node_name
|
327
|
-
alias :name= :node_name=
|
328
|
-
alias :type :node_type
|
329
|
-
alias :to_str :text
|
330
|
-
alias :clone :dup
|
331
|
-
alias :elements :element_children
|
332
|
-
|
333
408
|
####
|
334
|
-
#
|
335
|
-
#
|
336
|
-
|
337
|
-
|
338
|
-
|
409
|
+
# Set the Node's content to a Text node containing +string+. The string gets XML escaped, not
|
410
|
+
# interpreted as markup.
|
411
|
+
def content=(string)
|
412
|
+
self.native_content = encode_special_chars(string.to_s)
|
413
|
+
end
|
414
|
+
|
415
|
+
###
|
416
|
+
# Set the parent Node for this Node
|
417
|
+
def parent=(parent_node)
|
418
|
+
parent_node.add_child(self)
|
419
|
+
end
|
420
|
+
|
421
|
+
###
|
422
|
+
# Adds a default namespace supplied as a string +url+ href, to self.
|
423
|
+
# The consequence is as an xmlns attribute with supplied argument were
|
424
|
+
# present in parsed XML. A default namespace set with this method will
|
425
|
+
# now show up in #attributes, but when this node is serialized to XML an
|
426
|
+
# "xmlns" attribute will appear. See also #namespace and #namespace=
|
427
|
+
def default_namespace=(url)
|
428
|
+
add_namespace_definition(nil, url)
|
429
|
+
end
|
430
|
+
|
431
|
+
###
|
432
|
+
# Set the default namespace on this node (as would be defined with an
|
433
|
+
# "xmlns=" attribute in XML source), as a Namespace object +ns+. Note that
|
434
|
+
# a Namespace added this way will NOT be serialized as an xmlns attribute
|
435
|
+
# for this node. You probably want #default_namespace= instead, or perhaps
|
436
|
+
# #add_namespace_definition with a nil prefix argument.
|
437
|
+
def namespace=(ns)
|
438
|
+
return set_namespace(ns) unless ns
|
439
|
+
|
440
|
+
unless Nokogiri::XML::Namespace === ns
|
441
|
+
raise TypeError, "#{ns.class} can't be coerced into Nokogiri::XML::Namespace"
|
442
|
+
end
|
443
|
+
if ns.document != document
|
444
|
+
raise ArgumentError, "namespace must be declared on the same document"
|
445
|
+
end
|
446
|
+
|
447
|
+
set_namespace(ns)
|
448
|
+
end
|
449
|
+
|
450
|
+
###
|
451
|
+
# Do xinclude substitution on the subtree below node. If given a block, a
|
452
|
+
# Nokogiri::XML::ParseOptions object initialized from +options+, will be
|
453
|
+
# passed to it, allowing more convenient modification of the parser options.
|
454
|
+
def do_xinclude(options = XML::ParseOptions::DEFAULT_XML)
|
455
|
+
options = Nokogiri::XML::ParseOptions.new(options) if Integer === options
|
456
|
+
yield options if block_given?
|
457
|
+
|
458
|
+
# call c extension
|
459
|
+
process_xincludes(options.to_i)
|
460
|
+
end
|
461
|
+
|
462
|
+
alias_method :next, :next_sibling
|
463
|
+
alias_method :previous, :previous_sibling
|
464
|
+
alias_method :next=, :add_next_sibling
|
465
|
+
alias_method :previous=, :add_previous_sibling
|
466
|
+
alias_method :remove, :unlink
|
467
|
+
alias_method :name=, :node_name=
|
468
|
+
alias_method :add_namespace, :add_namespace_definition
|
469
|
+
|
470
|
+
# :section:
|
471
|
+
|
472
|
+
alias_method :inner_text, :content
|
473
|
+
alias_method :text, :content
|
474
|
+
alias_method :to_str, :content
|
475
|
+
alias_method :name, :node_name
|
476
|
+
alias_method :type, :node_type
|
477
|
+
alias_method :clone, :dup
|
478
|
+
alias_method :elements, :element_children
|
479
|
+
|
480
|
+
# :section: Working With Node Attributes
|
481
|
+
|
482
|
+
# :call-seq: [](name) → (String, nil)
|
483
|
+
#
|
484
|
+
# Fetch an attribute from this node.
|
485
|
+
#
|
486
|
+
# ⚠ Note that attributes with namespaces cannot be accessed with this method. To access
|
487
|
+
# namespaced attributes, use #attribute_with_ns.
|
488
|
+
#
|
489
|
+
# [Returns] (String, nil) value of the attribute +name+, or +nil+ if no matching attribute exists
|
490
|
+
#
|
491
|
+
# *Example*
|
492
|
+
#
|
493
|
+
# doc = Nokogiri::XML("<root><child size='large' class='big wide tall'/></root>")
|
494
|
+
# child = doc.at_css("child")
|
495
|
+
# child["size"] # => "large"
|
496
|
+
# child["class"] # => "big wide tall"
|
497
|
+
#
|
498
|
+
# *Example:* Namespaced attributes will not be returned.
|
499
|
+
#
|
500
|
+
# ⚠ Note namespaced attributes may be accessed with #attribute or #attribute_with_ns
|
501
|
+
#
|
502
|
+
# doc = Nokogiri::XML(<<~EOF)
|
503
|
+
# <root xmlns:width='http://example.com/widths'>
|
504
|
+
# <child width:size='broad'/>
|
505
|
+
# </root>
|
506
|
+
# EOF
|
507
|
+
# doc.at_css("child")["size"] # => nil
|
508
|
+
# doc.at_css("child").attribute("size").value # => "broad"
|
509
|
+
# doc.at_css("child").attribute_with_ns("size", "http://example.com/widths").value
|
510
|
+
# # => "broad"
|
511
|
+
#
|
512
|
+
def [](name)
|
513
|
+
get(name.to_s)
|
514
|
+
end
|
515
|
+
|
516
|
+
# :call-seq: []=(name, value) → value
|
517
|
+
#
|
518
|
+
# Update the attribute +name+ to +value+, or create the attribute if it does not exist.
|
519
|
+
#
|
520
|
+
# ⚠ Note that attributes with namespaces cannot be accessed with this method. To access
|
521
|
+
# namespaced attributes for update, use #attribute_with_ns. To add a namespaced attribute,
|
522
|
+
# see the example below.
|
523
|
+
#
|
524
|
+
# [Returns] +value+
|
525
|
+
#
|
526
|
+
# *Example*
|
527
|
+
#
|
528
|
+
# doc = Nokogiri::XML("<root><child/></root>")
|
529
|
+
# child = doc.at_css("child")
|
530
|
+
# child["size"] = "broad"
|
531
|
+
# child.to_html
|
532
|
+
# # => "<child size=\"broad\"></child>"
|
533
|
+
#
|
534
|
+
# *Example:* Add a namespaced attribute.
|
535
|
+
#
|
536
|
+
# doc = Nokogiri::XML(<<~EOF)
|
537
|
+
# <root xmlns:width='http://example.com/widths'>
|
538
|
+
# <child/>
|
539
|
+
# </root>
|
540
|
+
# EOF
|
541
|
+
# child = doc.at_css("child")
|
542
|
+
# child["size"] = "broad"
|
543
|
+
# ns = doc.root.namespace_definitions.find { |ns| ns.prefix == "width" }
|
544
|
+
# child.attribute("size").namespace = ns
|
545
|
+
# doc.to_html
|
546
|
+
# # => "<root xmlns:width=\"http://example.com/widths\">\n" +
|
547
|
+
# # " <child width:size=\"broad\"></child>\n" +
|
548
|
+
# # "</root>\n"
|
549
|
+
#
|
550
|
+
def []=(name, value)
|
551
|
+
set(name.to_s, value.to_s)
|
552
|
+
end
|
553
|
+
|
554
|
+
#
|
555
|
+
# :call-seq: attributes() → Hash<String ⇒ Nokogiri::XML::Attr>
|
556
|
+
#
|
557
|
+
# Fetch this node's attributes.
|
558
|
+
#
|
559
|
+
# ⚠ Because the keys do not include any namespace information for the attribute, in case of a
|
560
|
+
# simple name collision, not all attributes will be returned. In this case, you will need to
|
561
|
+
# use #attribute_nodes.
|
562
|
+
#
|
563
|
+
# [Returns]
|
564
|
+
# Hash containing attributes belonging to +self+. The hash keys are String attribute
|
565
|
+
# names (without the namespace), and the hash values are Nokogiri::XML::Attr.
|
566
|
+
#
|
567
|
+
# *Example* with no namespaces:
|
568
|
+
#
|
569
|
+
# doc = Nokogiri::XML("<root><child size='large' class='big wide tall'/></root>")
|
570
|
+
# doc.at_css("child").attributes
|
571
|
+
# # => {"size"=>#(Attr:0x550 { name = "size", value = "large" }),
|
572
|
+
# # "class"=>#(Attr:0x564 { name = "class", value = "big wide tall" })}
|
573
|
+
#
|
574
|
+
# *Example* with a namespace:
|
575
|
+
#
|
576
|
+
# doc = Nokogiri::XML("<root xmlns:desc='http://example.com/sizes'><child desc:size='large'/></root>")
|
577
|
+
# doc.at_css("child").attributes
|
578
|
+
# # => {"size"=>
|
579
|
+
# # #(Attr:0x550 {
|
580
|
+
# # name = "size",
|
581
|
+
# # namespace = #(Namespace:0x564 {
|
582
|
+
# # prefix = "desc",
|
583
|
+
# # href = "http://example.com/sizes"
|
584
|
+
# # }),
|
585
|
+
# # value = "large"
|
586
|
+
# # })}
|
587
|
+
#
|
588
|
+
# *Example* with an attribute name collision:
|
589
|
+
#
|
590
|
+
# ⚠ Note that only one of the attributes is returned in the Hash.
|
591
|
+
#
|
592
|
+
# doc = Nokogiri::XML(<<~EOF)
|
593
|
+
# <root xmlns:width='http://example.com/widths'
|
594
|
+
# xmlns:height='http://example.com/heights'>
|
595
|
+
# <child width:size='broad' height:size='tall'/>
|
596
|
+
# </root>
|
597
|
+
# EOF
|
598
|
+
# doc.at_css("child").attributes
|
599
|
+
# # => {"size"=>
|
600
|
+
# # #(Attr:0x550 {
|
601
|
+
# # name = "size",
|
602
|
+
# # namespace = #(Namespace:0x564 {
|
603
|
+
# # prefix = "height",
|
604
|
+
# # href = "http://example.com/heights"
|
605
|
+
# # }),
|
606
|
+
# # value = "tall"
|
607
|
+
# # })}
|
608
|
+
#
|
339
609
|
def attributes
|
340
|
-
|
341
|
-
[node.node_name
|
342
|
-
|
610
|
+
attribute_nodes.each_with_object({}) do |node, hash|
|
611
|
+
hash[node.node_name] = node
|
612
|
+
end
|
343
613
|
end
|
344
614
|
|
345
615
|
###
|
@@ -348,6 +618,12 @@ module Nokogiri
|
|
348
618
|
attribute_nodes.map(&:value)
|
349
619
|
end
|
350
620
|
|
621
|
+
###
|
622
|
+
# Does this Node's attributes include <value>
|
623
|
+
def value?(value)
|
624
|
+
values.include?(value)
|
625
|
+
end
|
626
|
+
|
351
627
|
###
|
352
628
|
# Get the attribute names for this Node.
|
353
629
|
def keys
|
@@ -357,97 +633,401 @@ module Nokogiri
|
|
357
633
|
###
|
358
634
|
# Iterate over each attribute name and value pair for this Node.
|
359
635
|
def each
|
360
|
-
attribute_nodes.each
|
636
|
+
attribute_nodes.each do |node|
|
361
637
|
yield [node.node_name, node.value]
|
362
|
-
|
638
|
+
end
|
363
639
|
end
|
364
640
|
|
365
641
|
###
|
366
|
-
#
|
367
|
-
|
642
|
+
# Remove the attribute named +name+
|
643
|
+
def remove_attribute(name)
|
644
|
+
attr = attributes[name].remove if key?(name)
|
645
|
+
clear_xpath_context if Nokogiri.jruby?
|
646
|
+
attr
|
647
|
+
end
|
648
|
+
|
649
|
+
#
|
650
|
+
# :call-seq: classes() → Array<String>
|
651
|
+
#
|
652
|
+
# Fetch CSS class names of a Node.
|
653
|
+
#
|
654
|
+
# This is a convenience function and is equivalent to:
|
655
|
+
#
|
656
|
+
# node.kwattr_values("class")
|
657
|
+
#
|
658
|
+
# See related: #kwattr_values, #add_class, #append_class, #remove_class
|
659
|
+
#
|
660
|
+
# [Returns]
|
661
|
+
# The CSS classes (Array of String) present in the Node's "class" attribute. If the
|
662
|
+
# attribute is empty or non-existent, the return value is an empty array.
|
663
|
+
#
|
664
|
+
# *Example*
|
665
|
+
#
|
666
|
+
# node # => <div class="section title header"></div>
|
667
|
+
# node.classes # => ["section", "title", "header"]
|
668
|
+
#
|
368
669
|
def classes
|
369
|
-
|
670
|
+
kwattr_values("class")
|
370
671
|
end
|
371
672
|
|
372
|
-
###
|
373
|
-
# Add +name+ to the "class" attribute value of this Node and
|
374
|
-
# return self. If the value is already in the current value, it
|
375
|
-
# is not added. If no "class" attribute exists yet, one is
|
376
|
-
# created with the given value.
|
377
673
|
#
|
378
|
-
#
|
379
|
-
#
|
380
|
-
|
381
|
-
|
382
|
-
|
674
|
+
# :call-seq: add_class(names) → self
|
675
|
+
#
|
676
|
+
# Ensure HTML CSS classes are present on +self+. Any CSS classes in +names+ that already exist
|
677
|
+
# in the "class" attribute are _not_ added. Note that any existing duplicates in the
|
678
|
+
# "class" attribute are not removed. Compare with #append_class.
|
679
|
+
#
|
680
|
+
# This is a convenience function and is equivalent to:
|
681
|
+
#
|
682
|
+
# node.kwattr_add("class", names)
|
683
|
+
#
|
684
|
+
# See related: #kwattr_add, #classes, #append_class, #remove_class
|
685
|
+
#
|
686
|
+
# [Parameters]
|
687
|
+
# - +names+ (String, Array<String>)
|
688
|
+
#
|
689
|
+
# CSS class names to be added to the Node's "class" attribute. May be a string containing
|
690
|
+
# whitespace-delimited names, or an Array of String names. Any class names already present
|
691
|
+
# will not be added. Any class names not present will be added. If no "class" attribute
|
692
|
+
# exists, one is created.
|
693
|
+
#
|
694
|
+
# [Returns] +self+ (Node) for ease of chaining method calls.
|
695
|
+
#
|
696
|
+
# *Example:* Ensure that the node has CSS class "section"
|
697
|
+
#
|
698
|
+
# node # => <div></div>
|
699
|
+
# node.add_class("section") # => <div class="section"></div>
|
700
|
+
# node.add_class("section") # => <div class="section"></div> # duplicate not added
|
701
|
+
#
|
702
|
+
# *Example:* Ensure that the node has CSS classes "section" and "header", via a String argument
|
703
|
+
#
|
704
|
+
# Note that the CSS class "section" is not added because it is already present.
|
705
|
+
# Note also that the pre-existing duplicate CSS class "section" is not removed.
|
706
|
+
#
|
707
|
+
# node # => <div class="section section"></div>
|
708
|
+
# node.add_class("section header") # => <div class="section section header"></div>
|
709
|
+
#
|
710
|
+
# *Example:* Ensure that the node has CSS classes "section" and "header", via an Array argument
|
711
|
+
#
|
712
|
+
# node # => <div></div>
|
713
|
+
# node.add_class(["section", "header"]) # => <div class="section header"></div>
|
714
|
+
#
|
715
|
+
def add_class(names)
|
716
|
+
kwattr_add("class", names)
|
717
|
+
end
|
718
|
+
|
719
|
+
#
|
720
|
+
# :call-seq: append_class(names) → self
|
721
|
+
#
|
722
|
+
# Add HTML CSS classes to +self+, regardless of duplication. Compare with #add_class.
|
723
|
+
#
|
724
|
+
# This is a convenience function and is equivalent to:
|
725
|
+
#
|
726
|
+
# node.kwattr_append("class", names)
|
727
|
+
#
|
728
|
+
# See related: #kwattr_append, #classes, #add_class, #remove_class
|
729
|
+
#
|
730
|
+
# [Parameters]
|
731
|
+
# - +names+ (String, Array<String>)
|
732
|
+
#
|
733
|
+
# CSS class names to be appended to the Node's "class" attribute. May be a string containing
|
734
|
+
# whitespace-delimited names, or an Array of String names. All class names passed in will be
|
735
|
+
# appended to the "class" attribute even if they are already present in the attribute
|
736
|
+
# value. If no "class" attribute exists, one is created.
|
737
|
+
#
|
738
|
+
# [Returns] +self+ (Node) for ease of chaining method calls.
|
739
|
+
#
|
740
|
+
# *Example:* Append "section" to the node's CSS "class" attribute
|
741
|
+
#
|
742
|
+
# node # => <div></div>
|
743
|
+
# node.append_class("section") # => <div class="section"></div>
|
744
|
+
# node.append_class("section") # => <div class="section section"></div> # duplicate added!
|
745
|
+
#
|
746
|
+
# *Example:* Append "section" and "header" to the noded's CSS "class" attribute, via a String argument
|
747
|
+
#
|
748
|
+
# Note that the CSS class "section" is appended even though it is already present
|
749
|
+
#
|
750
|
+
# node # => <div class="section section"></div>
|
751
|
+
# node.append_class("section header") # => <div class="section section section header"></div>
|
752
|
+
#
|
753
|
+
# *Example:* Append "section" and "header" to the node's CSS "class" attribute, via an Array argument
|
754
|
+
#
|
755
|
+
# node # => <div></div>
|
756
|
+
# node.append_class(["section", "header"]) # => <div class="section header"></div>
|
757
|
+
# node.append_class(["section", "header"]) # => <div class="section header section header"></div>
|
758
|
+
#
|
759
|
+
def append_class(names)
|
760
|
+
kwattr_append("class", names)
|
761
|
+
end
|
762
|
+
|
763
|
+
# :call-seq:
|
764
|
+
# remove_class(css_classes) → self
|
765
|
+
#
|
766
|
+
# Remove HTML CSS classes from this node. Any CSS class names in +css_classes+ that exist in
|
767
|
+
# this node's "class" attribute are removed, including any multiple entries.
|
768
|
+
#
|
769
|
+
# If no CSS classes remain after this operation, or if +css_classes+ is +nil+, the "class"
|
770
|
+
# attribute is deleted from the node.
|
771
|
+
#
|
772
|
+
# This is a convenience function and is equivalent to:
|
773
|
+
#
|
774
|
+
# node.kwattr_remove("class", css_classes)
|
775
|
+
#
|
776
|
+
# Also see #kwattr_remove, #classes, #add_class, #append_class
|
777
|
+
#
|
778
|
+
# [Parameters]
|
779
|
+
# - +css_classes+ (String, Array<String>)
|
780
|
+
#
|
781
|
+
# CSS class names to be removed from the Node's
|
782
|
+
# "class" attribute. May be a string containing whitespace-delimited names, or an Array of
|
783
|
+
# String names. Any class names already present will be removed. If no CSS classes remain,
|
784
|
+
# the "class" attribute is deleted.
|
785
|
+
#
|
786
|
+
# [Returns] +self+ (Nokogiri::XML::Node) for ease of chaining method calls.
|
787
|
+
#
|
788
|
+
# *Example*: Deleting a CSS class
|
789
|
+
#
|
790
|
+
# Note that all instances of the class "section" are removed from the "class" attribute.
|
791
|
+
#
|
792
|
+
# node # => <div class="section header section"></div>
|
793
|
+
# node.remove_class("section") # => <div class="header"></div>
|
794
|
+
#
|
795
|
+
# *Example*: Deleting the only remaining CSS class
|
796
|
+
#
|
797
|
+
# Note that the attribute is removed once there are no remaining classes.
|
798
|
+
#
|
799
|
+
# node # => <div class="section"></div>
|
800
|
+
# node.remove_class("section") # => <div></div>
|
801
|
+
#
|
802
|
+
# *Example*: Deleting multiple CSS classes
|
803
|
+
#
|
804
|
+
# Note that the "class" attribute is deleted once it's empty.
|
805
|
+
#
|
806
|
+
# node # => <div class="section header float"></div>
|
807
|
+
# node.remove_class(["section", "float"]) # => <div class="header"></div>
|
808
|
+
#
|
809
|
+
def remove_class(names = nil)
|
810
|
+
kwattr_remove("class", names)
|
811
|
+
end
|
812
|
+
|
813
|
+
# :call-seq:
|
814
|
+
# kwattr_values(attribute_name) → Array<String>
|
815
|
+
#
|
816
|
+
# Fetch values from a keyword attribute of a Node.
|
817
|
+
#
|
818
|
+
# A "keyword attribute" is a node attribute that contains a set of space-delimited
|
819
|
+
# values. Perhaps the most familiar example of this is the HTML "class" attribute used to
|
820
|
+
# contain CSS classes. But other keyword attributes exist, for instance
|
821
|
+
# {the "rel" attribute}[https://developer.mozilla.org/en-US/docs/Web/HTML/Attributes/rel].
|
822
|
+
#
|
823
|
+
# See also #classes, #kwattr_add, #kwattr_append, #kwattr_remove
|
824
|
+
#
|
825
|
+
# [Parameters]
|
826
|
+
# - +attribute_name+ (String) The name of the keyword attribute to be inspected.
|
827
|
+
#
|
828
|
+
# [Returns]
|
829
|
+
# (Array<String>) The values present in the Node's +attribute_name+ attribute. If the
|
830
|
+
# attribute is empty or non-existent, the return value is an empty array.
|
831
|
+
#
|
832
|
+
# *Example:*
|
833
|
+
#
|
834
|
+
# node # => <a rel="nofollow noopener external">link</a>
|
835
|
+
# node.kwattr_values("rel") # => ["nofollow", "noopener", "external"]
|
836
|
+
#
|
837
|
+
# Since v1.11.0
|
838
|
+
def kwattr_values(attribute_name)
|
839
|
+
keywordify(get_attribute(attribute_name) || [])
|
840
|
+
end
|
841
|
+
|
842
|
+
# :call-seq:
|
843
|
+
# kwattr_add(attribute_name, keywords) → self
|
844
|
+
#
|
845
|
+
# Ensure that values are present in a keyword attribute.
|
846
|
+
#
|
847
|
+
# Any values in +keywords+ that already exist in the Node's attribute values are _not_
|
848
|
+
# added. Note that any existing duplicates in the attribute values are not removed. Compare
|
849
|
+
# with #kwattr_append.
|
850
|
+
#
|
851
|
+
# A "keyword attribute" is a node attribute that contains a set of space-delimited
|
852
|
+
# values. Perhaps the most familiar example of this is the HTML "class" attribute used to
|
853
|
+
# contain CSS classes. But other keyword attributes exist, for instance
|
854
|
+
# {the "rel" attribute}[https://developer.mozilla.org/en-US/docs/Web/HTML/Attributes/rel].
|
855
|
+
#
|
856
|
+
# See also #add_class, #kwattr_values, #kwattr_append, #kwattr_remove
|
857
|
+
#
|
858
|
+
# [Parameters]
|
859
|
+
# - +attribute_name+ (String) The name of the keyword attribute to be modified.
|
860
|
+
# - +keywords+ (String, Array<String>)
|
861
|
+
# Keywords to be added to the attribute named +attribute_name+. May be a string containing
|
862
|
+
# whitespace-delimited values, or an Array of String values. Any values already present will
|
863
|
+
# not be added. Any values not present will be added. If the named attribute does not exist,
|
864
|
+
# it is created.
|
865
|
+
#
|
866
|
+
# [Returns] +self+ (Nokogiri::XML::Node) for ease of chaining method calls.
|
867
|
+
#
|
868
|
+
# *Example:* Ensure that a +Node+ has "nofollow" in its +rel+ attribute.
|
869
|
+
#
|
870
|
+
# Note that duplicates are not added.
|
871
|
+
#
|
872
|
+
# node # => <a></a>
|
873
|
+
# node.kwattr_add("rel", "nofollow") # => <a rel="nofollow"></a>
|
874
|
+
# node.kwattr_add("rel", "nofollow") # => <a rel="nofollow"></a>
|
875
|
+
#
|
876
|
+
# *Example:* Ensure that a +Node+ has "nofollow" and "noreferrer" in its +rel+ attribute, via a
|
877
|
+
# String argument.
|
878
|
+
#
|
879
|
+
# Note that "nofollow" is not added because it is already present. Note also that the
|
880
|
+
# pre-existing duplicate "nofollow" is not removed.
|
881
|
+
#
|
882
|
+
# node # => <a rel="nofollow nofollow"></a>
|
883
|
+
# node.kwattr_add("rel", "nofollow noreferrer") # => <a rel="nofollow nofollow noreferrer"></a>
|
884
|
+
#
|
885
|
+
# *Example:* Ensure that a +Node+ has "nofollow" and "noreferrer" in its +rel+ attribute, via
|
886
|
+
# an Array argument.
|
887
|
+
#
|
888
|
+
# node # => <a></a>
|
889
|
+
# node.kwattr_add("rel", ["nofollow", "noreferrer"]) # => <a rel="nofollow noreferrer"></a>
|
890
|
+
#
|
891
|
+
# Since v1.11.0
|
892
|
+
def kwattr_add(attribute_name, keywords)
|
893
|
+
keywords = keywordify(keywords)
|
894
|
+
current_kws = kwattr_values(attribute_name)
|
895
|
+
new_kws = (current_kws + (keywords - current_kws)).join(" ")
|
896
|
+
set_attribute(attribute_name, new_kws)
|
383
897
|
self
|
384
898
|
end
|
385
899
|
|
386
|
-
|
387
|
-
#
|
388
|
-
#
|
389
|
-
#
|
390
|
-
#
|
900
|
+
# :call-seq:
|
901
|
+
# kwattr_append(attribute_name, keywords) → self
|
902
|
+
#
|
903
|
+
# Add keywords to a Node's keyword attribute, regardless of duplication. Compare with
|
904
|
+
# #kwattr_add.
|
905
|
+
#
|
906
|
+
# A "keyword attribute" is a node attribute that contains a set of space-delimited
|
907
|
+
# values. Perhaps the most familiar example of this is the HTML "class" attribute used to
|
908
|
+
# contain CSS classes. But other keyword attributes exist, for instance
|
909
|
+
# {the "rel" attribute}[https://developer.mozilla.org/en-US/docs/Web/HTML/Attributes/rel].
|
910
|
+
#
|
911
|
+
# See also #append_class, #kwattr_values, #kwattr_add, #kwattr_remove
|
391
912
|
#
|
392
|
-
#
|
393
|
-
#
|
394
|
-
|
395
|
-
|
913
|
+
# [Parameters]
|
914
|
+
# - +attribute_name+ (String) The name of the keyword attribute to be modified.
|
915
|
+
# - +keywords+ (String, Array<String>)
|
916
|
+
# Keywords to be added to the attribute named +attribute_name+. May be a string containing
|
917
|
+
# whitespace-delimited values, or an Array of String values. All values passed in will be
|
918
|
+
# appended to the named attribute even if they are already present in the attribute. If the
|
919
|
+
# named attribute does not exist, it is created.
|
920
|
+
#
|
921
|
+
# [Returns] +self+ (Node) for ease of chaining method calls.
|
922
|
+
#
|
923
|
+
# *Example:* Append "nofollow" to the +rel+ attribute.
|
924
|
+
#
|
925
|
+
# Note that duplicates are added.
|
926
|
+
#
|
927
|
+
# node # => <a></a>
|
928
|
+
# node.kwattr_append("rel", "nofollow") # => <a rel="nofollow"></a>
|
929
|
+
# node.kwattr_append("rel", "nofollow") # => <a rel="nofollow nofollow"></a>
|
930
|
+
#
|
931
|
+
# *Example:* Append "nofollow" and "noreferrer" to the +rel+ attribute, via a String argument.
|
932
|
+
#
|
933
|
+
# Note that "nofollow" is appended even though it is already present.
|
934
|
+
#
|
935
|
+
# node # => <a rel="nofollow"></a>
|
936
|
+
# node.kwattr_append("rel", "nofollow noreferrer") # => <a rel="nofollow nofollow noreferrer"></a>
|
937
|
+
#
|
938
|
+
#
|
939
|
+
# *Example:* Append "nofollow" and "noreferrer" to the +rel+ attribute, via an Array argument.
|
940
|
+
#
|
941
|
+
# node # => <a></a>
|
942
|
+
# node.kwattr_append("rel", ["nofollow", "noreferrer"]) # => <a rel="nofollow noreferrer"></a>
|
943
|
+
#
|
944
|
+
# Since v1.11.0
|
945
|
+
def kwattr_append(attribute_name, keywords)
|
946
|
+
keywords = keywordify(keywords)
|
947
|
+
current_kws = kwattr_values(attribute_name)
|
948
|
+
new_kws = (current_kws + keywords).join(" ")
|
949
|
+
set_attribute(attribute_name, new_kws)
|
396
950
|
self
|
397
951
|
end
|
398
952
|
|
399
|
-
|
400
|
-
#
|
401
|
-
# and return self. If there are many occurrences of the name,
|
402
|
-
# they are all removed.
|
953
|
+
# :call-seq:
|
954
|
+
# kwattr_remove(attribute_name, keywords) → self
|
403
955
|
#
|
404
|
-
#
|
405
|
-
#
|
956
|
+
# Remove keywords from a keyword attribute. Any matching keywords that exist in the named
|
957
|
+
# attribute are removed, including any multiple entries.
|
406
958
|
#
|
407
|
-
# If no
|
408
|
-
#
|
409
|
-
|
410
|
-
|
411
|
-
|
412
|
-
|
413
|
-
|
414
|
-
|
415
|
-
|
416
|
-
|
959
|
+
# If no keywords remain after this operation, or if +keywords+ is +nil+, the attribute is
|
960
|
+
# deleted from the node.
|
961
|
+
#
|
962
|
+
# A "keyword attribute" is a node attribute that contains a set of space-delimited
|
963
|
+
# values. Perhaps the most familiar example of this is the HTML "class" attribute used to
|
964
|
+
# contain CSS classes. But other keyword attributes exist, for instance
|
965
|
+
# {the "rel" attribute}[https://developer.mozilla.org/en-US/docs/Web/HTML/Attributes/rel].
|
966
|
+
#
|
967
|
+
# See also #remove_class, #kwattr_values, #kwattr_add, #kwattr_append
|
968
|
+
#
|
969
|
+
# [Parameters]
|
970
|
+
# - +attribute_name+ (String) The name of the keyword attribute to be modified.
|
971
|
+
# - +keywords+ (String, Array<String>)
|
972
|
+
# Keywords to be removed from the attribute named +attribute_name+. May be a string
|
973
|
+
# containing whitespace-delimited values, or an Array of String values. Any keywords present
|
974
|
+
# in the named attribute will be removed. If no keywords remain, or if +keywords+ is nil,
|
975
|
+
# the attribute is deleted.
|
976
|
+
#
|
977
|
+
# [Returns] +self+ (Node) for ease of chaining method calls.
|
978
|
+
#
|
979
|
+
# *Example:*
|
980
|
+
#
|
981
|
+
# Note that the +rel+ attribute is deleted when empty.
|
982
|
+
#
|
983
|
+
# node # => <a rel="nofollow noreferrer">link</a>
|
984
|
+
# node.kwattr_remove("rel", "nofollow") # => <a rel="noreferrer">link</a>
|
985
|
+
# node.kwattr_remove("rel", "noreferrer") # => <a>link</a>
|
986
|
+
#
|
987
|
+
# Since v1.11.0
|
988
|
+
def kwattr_remove(attribute_name, keywords)
|
989
|
+
if keywords.nil?
|
990
|
+
remove_attribute(attribute_name)
|
991
|
+
return self
|
992
|
+
end
|
993
|
+
|
994
|
+
keywords = keywordify(keywords)
|
995
|
+
current_kws = kwattr_values(attribute_name)
|
996
|
+
new_kws = current_kws - keywords
|
997
|
+
if new_kws.empty?
|
998
|
+
remove_attribute(attribute_name)
|
417
999
|
else
|
418
|
-
|
1000
|
+
set_attribute(attribute_name, new_kws.join(" "))
|
419
1001
|
end
|
420
1002
|
self
|
421
1003
|
end
|
422
1004
|
|
423
|
-
|
424
|
-
|
425
|
-
|
426
|
-
|
427
|
-
|
428
|
-
|
429
|
-
|
430
|
-
alias :delete :remove_attribute
|
1005
|
+
alias_method :delete, :remove_attribute
|
1006
|
+
alias_method :get_attribute, :[]
|
1007
|
+
alias_method :attr, :[]
|
1008
|
+
alias_method :set_attribute, :[]=
|
1009
|
+
alias_method :has_attribute?, :key?
|
1010
|
+
|
1011
|
+
# :section:
|
431
1012
|
|
432
1013
|
###
|
433
1014
|
# Returns true if this Node matches +selector+
|
434
|
-
def matches?
|
1015
|
+
def matches?(selector)
|
435
1016
|
ancestors.last.search(selector).include?(self)
|
436
1017
|
end
|
437
1018
|
|
438
1019
|
###
|
439
1020
|
# Create a DocumentFragment containing +tags+ that is relative to _this_
|
440
1021
|
# context node.
|
441
|
-
def fragment
|
442
|
-
|
443
|
-
type::DocumentFragment.new(document, tags, self)
|
1022
|
+
def fragment(tags)
|
1023
|
+
document.related_class("DocumentFragment").new(document, tags, self)
|
444
1024
|
end
|
445
1025
|
|
446
1026
|
###
|
447
1027
|
# Parse +string_or_io+ as a document fragment within the context of
|
448
1028
|
# *this* node. Returns a XML::NodeSet containing the nodes parsed from
|
449
1029
|
# +string_or_io+.
|
450
|
-
def parse
|
1030
|
+
def parse(string_or_io, options = nil)
|
451
1031
|
##
|
452
1032
|
# When the current node is unparented and not an element node, use the
|
453
1033
|
# document as the parsing context instead. Otherwise, the in-context
|
@@ -458,61 +1038,93 @@ module Nokogiri
|
|
458
1038
|
end
|
459
1039
|
|
460
1040
|
options ||= (document.html? ? ParseOptions::DEFAULT_HTML : ParseOptions::DEFAULT_XML)
|
461
|
-
if Integer === options
|
462
|
-
options = Nokogiri::XML::ParseOptions.new(options)
|
463
|
-
end
|
464
|
-
# Give the options to the user
|
1041
|
+
options = Nokogiri::XML::ParseOptions.new(options) if Integer === options
|
465
1042
|
yield options if block_given?
|
466
1043
|
|
467
|
-
contents = string_or_io.respond_to?(:read)
|
468
|
-
string_or_io.read
|
1044
|
+
contents = if string_or_io.respond_to?(:read)
|
1045
|
+
string_or_io.read
|
1046
|
+
else
|
469
1047
|
string_or_io
|
1048
|
+
end
|
470
1049
|
|
471
1050
|
return Nokogiri::XML::NodeSet.new(document) if contents.empty?
|
472
1051
|
|
473
|
-
##
|
474
|
-
# This is a horrible hack, but I don't care. See #313 for background.
|
475
1052
|
error_count = document.errors.length
|
476
1053
|
node_set = in_context(contents, options.to_i)
|
477
|
-
if
|
478
|
-
|
479
|
-
|
1054
|
+
if document.errors.length > error_count
|
1055
|
+
raise document.errors[error_count] unless options.recover?
|
1056
|
+
|
1057
|
+
if node_set.empty?
|
1058
|
+
# libxml2 < 2.13 does not obey the +recover+ option after encountering errors during
|
1059
|
+
# +in_context+ parsing, and so this horrible hack is here to try to emulate recovery
|
1060
|
+
# behavior.
|
1061
|
+
#
|
1062
|
+
# (Note that HTML4 fragment parsing seems to have been fixed in abd74186, and XML
|
1063
|
+
# fragment parsing is fixed in 1c106edf. Both are in 2.13.)
|
1064
|
+
#
|
1065
|
+
# Unfortunately, this means we're no longer parsing "in context" and so namespaces that
|
1066
|
+
# would have been inherited from the context node won't be handled correctly. This hack
|
1067
|
+
# was written in 2010, and I regret it, because it's silently degrading functionality in
|
1068
|
+
# a way that's not easily prevented (or even detected).
|
1069
|
+
#
|
1070
|
+
# I think preferable behavior would be to either:
|
1071
|
+
#
|
1072
|
+
# a. add an error noting that we "fell back" and pointing the user to turning off the
|
1073
|
+
# +recover+ option
|
1074
|
+
# b. don't recover, but raise a sensible exception
|
1075
|
+
#
|
1076
|
+
# For context and background:
|
1077
|
+
# - https://github.com/sparklemotion/nokogiri/issues/313
|
1078
|
+
# - https://github.com/sparklemotion/nokogiri/issues/2092
|
1079
|
+
fragment = document.related_class("DocumentFragment").parse(contents)
|
1080
|
+
node_set = fragment.children
|
1081
|
+
end
|
480
1082
|
end
|
481
1083
|
node_set
|
482
1084
|
end
|
483
1085
|
|
484
|
-
|
485
|
-
#
|
486
|
-
|
487
|
-
|
488
|
-
|
489
|
-
|
490
|
-
|
491
|
-
#
|
492
|
-
|
493
|
-
|
494
|
-
|
495
|
-
|
496
|
-
|
497
|
-
|
498
|
-
#
|
499
|
-
#
|
1086
|
+
# :call-seq:
|
1087
|
+
# namespaces() → Hash<String(Namespace#prefix) ⇒ String(Namespace#href)>
|
1088
|
+
#
|
1089
|
+
# Fetch all the namespaces on this node and its ancestors.
|
1090
|
+
#
|
1091
|
+
# Note that the keys in this hash XML attributes that would be used to define this namespace,
|
1092
|
+
# such as "xmlns:prefix", not just the prefix.
|
1093
|
+
#
|
1094
|
+
# The default namespace for this node will be included with key "xmlns".
|
1095
|
+
#
|
1096
|
+
# See also #namespace_scopes
|
1097
|
+
#
|
1098
|
+
# [Returns]
|
1099
|
+
# Hash containing all the namespaces on this node and its ancestors. The hash keys are the
|
1100
|
+
# namespace prefix, and the hash value for each key is the namespace URI.
|
1101
|
+
#
|
1102
|
+
# *Example:*
|
500
1103
|
#
|
501
|
-
#
|
1104
|
+
# doc = Nokogiri::XML(<<~EOF)
|
1105
|
+
# <root xmlns="http://example.com/root" xmlns:in_scope="http://example.com/in_scope">
|
1106
|
+
# <first/>
|
1107
|
+
# <second xmlns="http://example.com/child"/>
|
1108
|
+
# <third xmlns:foo="http://example.com/foo"/>
|
1109
|
+
# </root>
|
1110
|
+
# EOF
|
1111
|
+
# doc.at_xpath("//root:first", "root" => "http://example.com/root").namespaces
|
1112
|
+
# # => {"xmlns"=>"http://example.com/root",
|
1113
|
+
# # "xmlns:in_scope"=>"http://example.com/in_scope"}
|
1114
|
+
# doc.at_xpath("//child:second", "child" => "http://example.com/child").namespaces
|
1115
|
+
# # => {"xmlns"=>"http://example.com/child",
|
1116
|
+
# # "xmlns:in_scope"=>"http://example.com/in_scope"}
|
1117
|
+
# doc.at_xpath("//root:third", "root" => "http://example.com/root").namespaces
|
1118
|
+
# # => {"xmlns:foo"=>"http://example.com/foo",
|
1119
|
+
# # "xmlns"=>"http://example.com/root",
|
1120
|
+
# # "xmlns:in_scope"=>"http://example.com/in_scope"}
|
502
1121
|
#
|
503
|
-
# Returns namespaces in scope for self -- those defined on self
|
504
|
-
# element directly or any ancestor node -- as a Hash of
|
505
|
-
# attribute-name/value pairs. Note that the keys in this hash
|
506
|
-
# XML attributes that would be used to define this namespace,
|
507
|
-
# such as "xmlns:prefix", not just the prefix. Default namespace
|
508
|
-
# set on self will be included with key "xmlns". However,
|
509
|
-
# default namespaces set on ancestor will NOT be, even if self
|
510
|
-
# has no explicit default namespace.
|
511
1122
|
def namespaces
|
512
|
-
|
513
|
-
|
514
|
-
|
515
|
-
|
1123
|
+
namespace_scopes.each_with_object({}) do |ns, hash|
|
1124
|
+
prefix = ns.prefix
|
1125
|
+
key = prefix ? "xmlns:#{prefix}" : "xmlns"
|
1126
|
+
hash[key] = ns.href
|
1127
|
+
end
|
516
1128
|
end
|
517
1129
|
|
518
1130
|
# Returns true if this is a Comment
|
@@ -530,14 +1142,14 @@ module Nokogiri
|
|
530
1142
|
type == DOCUMENT_NODE
|
531
1143
|
end
|
532
1144
|
|
533
|
-
# Returns true if this is an
|
1145
|
+
# Returns true if this is an HTML4::Document or HTML5::Document node
|
534
1146
|
def html?
|
535
1147
|
type == HTML_DOCUMENT_NODE
|
536
1148
|
end
|
537
1149
|
|
538
1150
|
# Returns true if this is a Document
|
539
1151
|
def document?
|
540
|
-
is_a?
|
1152
|
+
is_a?(XML::Document)
|
541
1153
|
end
|
542
1154
|
|
543
1155
|
# Returns true if this is a ProcessingInstruction node
|
@@ -556,11 +1168,12 @@ module Nokogiri
|
|
556
1168
|
end
|
557
1169
|
|
558
1170
|
###
|
559
|
-
# Fetch the Nokogiri::
|
1171
|
+
# Fetch the Nokogiri::HTML4::ElementDescription for this node. Returns
|
560
1172
|
# nil on XML documents and on unknown tags.
|
561
1173
|
def description
|
562
|
-
return
|
563
|
-
|
1174
|
+
return if document.xml?
|
1175
|
+
|
1176
|
+
Nokogiri::HTML4::ElementDescription[name]
|
564
1177
|
end
|
565
1178
|
|
566
1179
|
###
|
@@ -574,7 +1187,8 @@ module Nokogiri
|
|
574
1187
|
def element?
|
575
1188
|
type == ELEMENT_NODE
|
576
1189
|
end
|
577
|
-
|
1190
|
+
|
1191
|
+
alias_method :elem?, :element?
|
578
1192
|
|
579
1193
|
###
|
580
1194
|
# Turn this node in to a string. If the document is HTML, this method
|
@@ -584,28 +1198,29 @@ module Nokogiri
|
|
584
1198
|
end
|
585
1199
|
|
586
1200
|
# Get the inner_html for this node's Node#children
|
587
|
-
def inner_html
|
1201
|
+
def inner_html(*args)
|
588
1202
|
children.map { |x| x.to_html(*args) }.join
|
589
1203
|
end
|
590
1204
|
|
591
1205
|
# Get the path to this node as a CSS expression
|
592
1206
|
def css_path
|
593
|
-
path.split(
|
594
|
-
part.
|
595
|
-
|
1207
|
+
path.split(%r{/}).filter_map do |part|
|
1208
|
+
part.empty? ? nil : part.gsub(/\[(\d+)\]/, ':nth-of-type(\1)')
|
1209
|
+
end.join(" > ")
|
596
1210
|
end
|
597
1211
|
|
598
1212
|
###
|
599
1213
|
# Get a list of ancestor Node for this Node. If +selector+ is given,
|
600
1214
|
# the ancestors must match +selector+
|
601
|
-
def ancestors
|
1215
|
+
def ancestors(selector = nil)
|
602
1216
|
return NodeSet.new(document) unless respond_to?(:parent)
|
603
1217
|
return NodeSet.new(document) unless parent
|
604
1218
|
|
605
1219
|
parents = [parent]
|
606
1220
|
|
607
1221
|
while parents.last.respond_to?(:parent)
|
608
|
-
break unless ctx_parent = parents.last.parent
|
1222
|
+
break unless (ctx_parent = parents.last.parent)
|
1223
|
+
|
609
1224
|
parents << ctx_parent
|
610
1225
|
end
|
611
1226
|
|
@@ -614,89 +1229,77 @@ module Nokogiri
|
|
614
1229
|
root = parents.last
|
615
1230
|
search_results = root.search(selector)
|
616
1231
|
|
617
|
-
NodeSet.new(document, parents.find_all
|
1232
|
+
NodeSet.new(document, parents.find_all do |parent|
|
618
1233
|
search_results.include?(parent)
|
619
|
-
|
620
|
-
end
|
621
|
-
|
622
|
-
###
|
623
|
-
# Adds a default namespace supplied as a string +url+ href, to self.
|
624
|
-
# The consequence is as an xmlns attribute with supplied argument were
|
625
|
-
# present in parsed XML. A default namespace set with this method will
|
626
|
-
# now show up in #attributes, but when this node is serialized to XML an
|
627
|
-
# "xmlns" attribute will appear. See also #namespace and #namespace=
|
628
|
-
def default_namespace= url
|
629
|
-
add_namespace_definition(nil, url)
|
630
|
-
end
|
631
|
-
alias :add_namespace :add_namespace_definition
|
632
|
-
|
633
|
-
###
|
634
|
-
# Set the default namespace on this node (as would be defined with an
|
635
|
-
# "xmlns=" attribute in XML source), as a Namespace object +ns+. Note that
|
636
|
-
# a Namespace added this way will NOT be serialized as an xmlns attribute
|
637
|
-
# for this node. You probably want #default_namespace= instead, or perhaps
|
638
|
-
# #add_namespace_definition with a nil prefix argument.
|
639
|
-
def namespace= ns
|
640
|
-
return set_namespace(ns) unless ns
|
641
|
-
|
642
|
-
unless Nokogiri::XML::Namespace === ns
|
643
|
-
raise TypeError, "#{ns.class} can't be coerced into Nokogiri::XML::Namespace"
|
644
|
-
end
|
645
|
-
if ns.document != document
|
646
|
-
raise ArgumentError, 'namespace must be declared on the same document'
|
647
|
-
end
|
648
|
-
|
649
|
-
set_namespace ns
|
1234
|
+
end)
|
650
1235
|
end
|
651
1236
|
|
652
1237
|
####
|
653
1238
|
# Yields self and all children to +block+ recursively.
|
654
|
-
def traverse
|
655
|
-
children.each{|j| j.traverse(&block) }
|
656
|
-
|
1239
|
+
def traverse(&block)
|
1240
|
+
children.each { |j| j.traverse(&block) }
|
1241
|
+
yield(self)
|
657
1242
|
end
|
658
1243
|
|
659
1244
|
###
|
660
1245
|
# Accept a visitor. This method calls "visit" on +visitor+ with self.
|
661
|
-
def accept
|
1246
|
+
def accept(visitor)
|
662
1247
|
visitor.visit(self)
|
663
1248
|
end
|
664
1249
|
|
665
1250
|
###
|
666
1251
|
# Test to see if this Node is equal to +other+
|
667
|
-
def ==
|
1252
|
+
def ==(other)
|
668
1253
|
return false unless other
|
669
1254
|
return false unless other.respond_to?(:pointer_id)
|
1255
|
+
|
670
1256
|
pointer_id == other.pointer_id
|
671
1257
|
end
|
672
1258
|
|
673
1259
|
###
|
674
|
-
#
|
675
|
-
#
|
1260
|
+
# Compare two Node objects with respect to their Document. Nodes from
|
1261
|
+
# different documents cannot be compared.
|
1262
|
+
def <=>(other)
|
1263
|
+
return unless other.is_a?(Nokogiri::XML::Node)
|
1264
|
+
return unless document == other.document
|
1265
|
+
|
1266
|
+
compare(other)
|
1267
|
+
end
|
1268
|
+
|
1269
|
+
# :section: Serialization and Generating Output
|
1270
|
+
|
1271
|
+
###
|
1272
|
+
# Serialize Node using +options+. Save options can also be set using a block.
|
1273
|
+
#
|
1274
|
+
# See also Nokogiri::XML::Node::SaveOptions and Node@Serialization+and+Generating+Output.
|
676
1275
|
#
|
677
1276
|
# These two statements are equivalent:
|
678
1277
|
#
|
679
|
-
#
|
1278
|
+
# node.serialize(encoding: 'UTF-8', save_with: FORMAT | AS_XML)
|
680
1279
|
#
|
681
1280
|
# or
|
682
1281
|
#
|
683
|
-
# node.serialize(:
|
1282
|
+
# node.serialize(encoding: 'UTF-8') do |config|
|
684
1283
|
# config.format.as_xml
|
685
1284
|
# end
|
686
1285
|
#
|
687
|
-
def serialize
|
688
|
-
options
|
689
|
-
|
690
|
-
|
691
|
-
|
1286
|
+
def serialize(*args, &block)
|
1287
|
+
# TODO: deprecate non-hash options, see 46c68ed 2009-06-20 for context
|
1288
|
+
options = if args.first.is_a?(Hash)
|
1289
|
+
args.shift
|
1290
|
+
else
|
1291
|
+
{
|
1292
|
+
encoding: args[0],
|
1293
|
+
save_with: args[1],
|
1294
|
+
}
|
1295
|
+
end
|
1296
|
+
|
1297
|
+
options[:encoding] ||= document.encoding
|
1298
|
+
encoding = Encoding.find(options[:encoding] || "UTF-8")
|
692
1299
|
|
693
|
-
|
694
|
-
options[:encoding] = encoding
|
1300
|
+
io = StringIO.new(String.new(encoding: encoding))
|
695
1301
|
|
696
|
-
|
697
|
-
outstring.force_encoding(Encoding.find(encoding || 'utf-8'))
|
698
|
-
io = StringIO.new(outstring)
|
699
|
-
write_to io, options, &block
|
1302
|
+
write_to(io, options, &block)
|
700
1303
|
io.string
|
701
1304
|
end
|
702
1305
|
|
@@ -707,17 +1310,17 @@ module Nokogiri
|
|
707
1310
|
#
|
708
1311
|
# See Node#write_to for a list of +options+. For formatted output,
|
709
1312
|
# use Node#to_xhtml instead.
|
710
|
-
def to_html
|
711
|
-
to_format
|
1313
|
+
def to_html(options = {})
|
1314
|
+
to_format(SaveOptions::DEFAULT_HTML, options)
|
712
1315
|
end
|
713
1316
|
|
714
1317
|
###
|
715
1318
|
# Serialize this Node to XML using +options+
|
716
1319
|
#
|
717
|
-
# doc.to_xml(:
|
1320
|
+
# doc.to_xml(indent: 5, encoding: 'UTF-8')
|
718
1321
|
#
|
719
1322
|
# See Node#write_to for a list of +options+
|
720
|
-
def to_xml
|
1323
|
+
def to_xml(options = {})
|
721
1324
|
options[:save_with] ||= SaveOptions::DEFAULT_XML
|
722
1325
|
serialize(options)
|
723
1326
|
end
|
@@ -725,62 +1328,76 @@ module Nokogiri
|
|
725
1328
|
###
|
726
1329
|
# Serialize this Node to XHTML using +options+
|
727
1330
|
#
|
728
|
-
# doc.to_xhtml(:
|
1331
|
+
# doc.to_xhtml(indent: 5, encoding: 'UTF-8')
|
729
1332
|
#
|
730
1333
|
# See Node#write_to for a list of +options+
|
731
|
-
def to_xhtml
|
732
|
-
to_format
|
1334
|
+
def to_xhtml(options = {})
|
1335
|
+
to_format(SaveOptions::DEFAULT_XHTML, options)
|
733
1336
|
end
|
734
1337
|
|
735
1338
|
###
|
736
|
-
#
|
737
|
-
#
|
1339
|
+
# :call-seq:
|
1340
|
+
# write_to(io, *options)
|
1341
|
+
#
|
1342
|
+
# Serialize this node or document to +io+.
|
1343
|
+
#
|
1344
|
+
# [Parameters]
|
1345
|
+
# - +io+ (IO) An IO-like object to which the serialized content will be written.
|
1346
|
+
# - +options+ (Hash) See below
|
738
1347
|
#
|
739
|
-
#
|
740
|
-
# * +:
|
741
|
-
# * +:
|
742
|
-
# * +:
|
1348
|
+
# [Options]
|
1349
|
+
# * +:encoding+ (String or Encoding) specify the encoding of the output (defaults to document encoding)
|
1350
|
+
# * +:indent_text+ (String) the indentation text (defaults to <code>" "</code>)
|
1351
|
+
# * +:indent+ (Integer) the number of +:indent_text+ to use (defaults to +2+)
|
1352
|
+
# * +:save_with+ (Integer) a combination of SaveOptions constants
|
743
1353
|
#
|
744
1354
|
# To save with UTF-8 indented twice:
|
745
1355
|
#
|
746
|
-
# node.write_to(io, :
|
1356
|
+
# node.write_to(io, encoding: 'UTF-8', indent: 2)
|
747
1357
|
#
|
748
1358
|
# To save indented with two dashes:
|
749
1359
|
#
|
750
|
-
# node.write_to(io, :
|
1360
|
+
# node.write_to(io, indent_text: '-', indent: 2)
|
751
1361
|
#
|
752
|
-
def write_to
|
753
|
-
options
|
754
|
-
encoding
|
1362
|
+
def write_to(io, *options)
|
1363
|
+
options = options.first.is_a?(Hash) ? options.shift : {}
|
1364
|
+
encoding = options[:encoding] || options[0] || document.encoding
|
755
1365
|
if Nokogiri.jruby?
|
756
|
-
save_options
|
757
|
-
indent_times
|
1366
|
+
save_options = options[:save_with] || options[1]
|
1367
|
+
indent_times = options[:indent] || 0
|
758
1368
|
else
|
759
|
-
save_options
|
760
|
-
indent_times
|
1369
|
+
save_options = options[:save_with] || options[1] || SaveOptions::FORMAT
|
1370
|
+
indent_times = options[:indent] || 2
|
761
1371
|
end
|
762
|
-
indent_text
|
1372
|
+
indent_text = options[:indent_text] || " "
|
1373
|
+
|
1374
|
+
# Any string times 0 returns an empty string. Therefore, use the same
|
1375
|
+
# string instead of generating a new empty string for every node with
|
1376
|
+
# zero indentation.
|
1377
|
+
indentation = indent_times.zero? ? "" : (indent_text * indent_times)
|
763
1378
|
|
764
1379
|
config = SaveOptions.new(save_options.to_i)
|
765
1380
|
yield config if block_given?
|
766
1381
|
|
767
|
-
|
1382
|
+
encoding = encoding.is_a?(Encoding) ? encoding.name : encoding
|
1383
|
+
|
1384
|
+
native_write_to(io, encoding, indentation, config.options)
|
768
1385
|
end
|
769
1386
|
|
770
1387
|
###
|
771
1388
|
# Write Node as HTML to +io+ with +options+
|
772
1389
|
#
|
773
1390
|
# See Node#write_to for a list of +options+
|
774
|
-
def write_html_to
|
775
|
-
write_format_to
|
1391
|
+
def write_html_to(io, options = {})
|
1392
|
+
write_format_to(SaveOptions::DEFAULT_HTML, io, options)
|
776
1393
|
end
|
777
1394
|
|
778
1395
|
###
|
779
1396
|
# Write Node as XHTML to +io+ with +options+
|
780
1397
|
#
|
781
1398
|
# See Node#write_to for a list of +options+
|
782
|
-
def write_xhtml_to
|
783
|
-
write_format_to
|
1399
|
+
def write_xhtml_to(io, options = {})
|
1400
|
+
write_format_to(SaveOptions::DEFAULT_XHTML, io, options)
|
784
1401
|
end
|
785
1402
|
|
786
1403
|
###
|
@@ -789,110 +1406,168 @@ module Nokogiri
|
|
789
1406
|
# doc.write_xml_to io, :encoding => 'UTF-8'
|
790
1407
|
#
|
791
1408
|
# See Node#write_to for a list of options
|
792
|
-
def write_xml_to
|
1409
|
+
def write_xml_to(io, options = {})
|
793
1410
|
options[:save_with] ||= SaveOptions::DEFAULT_XML
|
794
|
-
write_to
|
1411
|
+
write_to(io, options)
|
795
1412
|
end
|
796
1413
|
|
797
|
-
|
798
|
-
|
799
|
-
|
800
|
-
|
801
|
-
|
802
|
-
|
803
|
-
compare other
|
1414
|
+
def canonicalize(mode = XML::XML_C14N_1_0, inclusive_namespaces = nil, with_comments = false)
|
1415
|
+
c14n_root = self
|
1416
|
+
document.canonicalize(mode, inclusive_namespaces, with_comments) do |node, parent|
|
1417
|
+
tn = node.is_a?(XML::Node) ? node : parent
|
1418
|
+
tn == c14n_root || tn.ancestors.include?(c14n_root)
|
1419
|
+
end
|
804
1420
|
end
|
805
1421
|
|
806
|
-
|
807
|
-
|
808
|
-
# Nokogiri::XML::ParseOptions object initialized from +options+, will be
|
809
|
-
# passed to it, allowing more convenient modification of the parser options.
|
810
|
-
def do_xinclude options = XML::ParseOptions::DEFAULT_XML
|
811
|
-
options = Nokogiri::XML::ParseOptions.new(options) if Integer === options
|
1422
|
+
DECONSTRUCT_KEYS = [:name, :attributes, :children, :namespace, :content, :elements, :inner_html].freeze # :nodoc:
|
1423
|
+
DECONSTRUCT_METHODS = { attributes: :attribute_nodes }.freeze # :nodoc:
|
812
1424
|
|
813
|
-
|
814
|
-
|
815
|
-
|
816
|
-
|
817
|
-
|
1425
|
+
#
|
1426
|
+
# :call-seq: deconstruct_keys(array_of_names) → Hash
|
1427
|
+
#
|
1428
|
+
# Returns a hash describing the Node, to use in pattern matching.
|
1429
|
+
#
|
1430
|
+
# Valid keys and their values:
|
1431
|
+
# - +name+ → (String) The name of this node, or "text" if it is a Text node.
|
1432
|
+
# - +namespace+ → (Namespace, nil) The namespace of this node, or nil if there is no namespace.
|
1433
|
+
# - +attributes+ → (Array<Attr>) The attributes of this node.
|
1434
|
+
# - +children+ → (Array<Node>) The children of this node. 💡 Note this includes text nodes.
|
1435
|
+
# - +elements+ → (Array<Node>) The child elements of this node. 💡 Note this does not include text nodes.
|
1436
|
+
# - +content+ → (String) The contents of all the text nodes in this node's subtree. See #content.
|
1437
|
+
# - +inner_html+ → (String) The inner markup for the children of this node. See #inner_html.
|
1438
|
+
#
|
1439
|
+
# *Example*
|
1440
|
+
#
|
1441
|
+
# doc = Nokogiri::XML.parse(<<~XML)
|
1442
|
+
# <?xml version="1.0"?>
|
1443
|
+
# <parent xmlns="http://nokogiri.org/ns/default" xmlns:noko="http://nokogiri.org/ns/noko">
|
1444
|
+
# <child1 foo="abc" noko:bar="def">First</child1>
|
1445
|
+
# <noko:child2 foo="qwe" noko:bar="rty">Second</noko:child2>
|
1446
|
+
# </parent>
|
1447
|
+
# XML
|
1448
|
+
#
|
1449
|
+
# doc.root.deconstruct_keys([:name, :namespace])
|
1450
|
+
# # => {:name=>"parent",
|
1451
|
+
# # :namespace=>
|
1452
|
+
# # #(Namespace:0x35c { href = "http://nokogiri.org/ns/default" })}
|
1453
|
+
#
|
1454
|
+
# doc.root.deconstruct_keys([:inner_html, :content])
|
1455
|
+
# # => {:content=>"\n" + " First\n" + " Second\n",
|
1456
|
+
# # :inner_html=>
|
1457
|
+
# # "\n" +
|
1458
|
+
# # " <child1 foo=\"abc\" noko:bar=\"def\">First</child1>\n" +
|
1459
|
+
# # " <noko:child2 foo=\"qwe\" noko:bar=\"rty\">Second</noko:child2>\n"}
|
1460
|
+
#
|
1461
|
+
# doc.root.elements.first.deconstruct_keys([:attributes])
|
1462
|
+
# # => {:attributes=>
|
1463
|
+
# # [#(Attr:0x370 { name = "foo", value = "abc" }),
|
1464
|
+
# # #(Attr:0x384 {
|
1465
|
+
# # name = "bar",
|
1466
|
+
# # namespace = #(Namespace:0x398 {
|
1467
|
+
# # prefix = "noko",
|
1468
|
+
# # href = "http://nokogiri.org/ns/noko"
|
1469
|
+
# # }),
|
1470
|
+
# # value = "def"
|
1471
|
+
# # })]}
|
1472
|
+
#
|
1473
|
+
# Since v1.14.0
|
1474
|
+
#
|
1475
|
+
def deconstruct_keys(keys)
|
1476
|
+
requested_keys = DECONSTRUCT_KEYS & keys
|
1477
|
+
{}.tap do |values|
|
1478
|
+
requested_keys.each do |key|
|
1479
|
+
method = DECONSTRUCT_METHODS[key] || key
|
1480
|
+
values[key] = send(method)
|
1481
|
+
end
|
1482
|
+
end
|
818
1483
|
end
|
819
1484
|
|
820
|
-
|
821
|
-
|
822
|
-
|
823
|
-
|
824
|
-
|
1485
|
+
# :section:
|
1486
|
+
|
1487
|
+
protected
|
1488
|
+
|
1489
|
+
def coerce(data)
|
1490
|
+
case data
|
1491
|
+
when XML::NodeSet
|
1492
|
+
return data
|
1493
|
+
when XML::DocumentFragment
|
1494
|
+
return data.children
|
1495
|
+
when String
|
1496
|
+
return fragment(data).children
|
1497
|
+
when Document, XML::Attr
|
1498
|
+
# unacceptable
|
1499
|
+
when XML::Node
|
1500
|
+
return data
|
825
1501
|
end
|
1502
|
+
|
1503
|
+
raise ArgumentError, <<~EOERR
|
1504
|
+
Requires a Node, NodeSet or String argument, and cannot accept a #{data.class}.
|
1505
|
+
(You probably want to select a node from the Document with at() or search(), or create a new Node via Node.new().)
|
1506
|
+
EOERR
|
826
1507
|
end
|
827
1508
|
|
828
1509
|
private
|
829
1510
|
|
830
|
-
def
|
831
|
-
|
832
|
-
|
1511
|
+
def keywordify(keywords)
|
1512
|
+
case keywords
|
1513
|
+
when Enumerable
|
1514
|
+
keywords
|
1515
|
+
when String
|
1516
|
+
keywords.scan(/\S+/)
|
1517
|
+
else
|
1518
|
+
raise ArgumentError,
|
1519
|
+
"Keyword attributes must be passed as either a String or an Enumerable, but received #{keywords.class}"
|
1520
|
+
end
|
1521
|
+
end
|
1522
|
+
|
1523
|
+
def add_sibling(next_or_previous, node_or_tags)
|
1524
|
+
raise("Cannot add sibling to a node with no parent") unless parent
|
833
1525
|
|
834
|
-
|
1526
|
+
impl = next_or_previous == :next ? :add_next_sibling_node : :add_previous_sibling_node
|
1527
|
+
iter = next_or_previous == :next ? :reverse_each : :each
|
1528
|
+
|
1529
|
+
node_or_tags = parent.coerce(node_or_tags)
|
835
1530
|
if node_or_tags.is_a?(XML::NodeSet)
|
836
1531
|
if text?
|
837
|
-
pivot = Nokogiri::XML::Node.new
|
838
|
-
send
|
1532
|
+
pivot = Nokogiri::XML::Node.new("dummy", document)
|
1533
|
+
send(impl, pivot)
|
839
1534
|
else
|
840
1535
|
pivot = self
|
841
1536
|
end
|
842
|
-
node_or_tags.send(iter) { |n| pivot.send
|
1537
|
+
node_or_tags.send(iter) { |n| pivot.send(impl, n) }
|
843
1538
|
pivot.unlink if text?
|
844
1539
|
else
|
845
|
-
send
|
1540
|
+
send(impl, node_or_tags)
|
846
1541
|
end
|
847
1542
|
node_or_tags
|
848
1543
|
end
|
849
1544
|
|
850
|
-
|
851
|
-
|
852
|
-
|
1545
|
+
USING_LIBXML_WITH_BROKEN_SERIALIZATION = Nokogiri.uses_libxml?("~> 2.6.0").freeze
|
1546
|
+
private_constant :USING_LIBXML_WITH_BROKEN_SERIALIZATION
|
1547
|
+
|
1548
|
+
def to_format(save_option, options)
|
1549
|
+
return dump_html if USING_LIBXML_WITH_BROKEN_SERIALIZATION
|
853
1550
|
|
854
1551
|
options[:save_with] = save_option unless options[:save_with]
|
855
1552
|
serialize(options)
|
856
1553
|
end
|
857
1554
|
|
858
|
-
def write_format_to
|
859
|
-
|
860
|
-
return (io << dump_html) if Nokogiri.uses_libxml? && %w[2 6] === LIBXML_VERSION.split('.')[0..1]
|
1555
|
+
def write_format_to(save_option, io, options)
|
1556
|
+
return (io << dump_html) if USING_LIBXML_WITH_BROKEN_SERIALIZATION
|
861
1557
|
|
862
1558
|
options[:save_with] ||= save_option
|
863
|
-
write_to
|
1559
|
+
write_to(io, options)
|
864
1560
|
end
|
865
1561
|
|
866
1562
|
def inspect_attributes
|
867
1563
|
[:name, :namespace, :attribute_nodes, :children]
|
868
1564
|
end
|
869
1565
|
|
870
|
-
|
871
|
-
case data
|
872
|
-
when XML::NodeSet
|
873
|
-
return data
|
874
|
-
when XML::DocumentFragment
|
875
|
-
return data.children
|
876
|
-
when String
|
877
|
-
return fragment(data).children
|
878
|
-
when Document, XML::Attr
|
879
|
-
# unacceptable
|
880
|
-
when XML::Node
|
881
|
-
return data
|
882
|
-
end
|
883
|
-
|
884
|
-
raise ArgumentError, <<-EOERR
|
885
|
-
Requires a Node, NodeSet or String argument, and cannot accept a #{data.class}.
|
886
|
-
(You probably want to select a node from the Document with at() or search(), or create a new Node via Node.new().)
|
887
|
-
EOERR
|
888
|
-
end
|
889
|
-
|
890
|
-
# @private
|
891
|
-
IMPLIED_XPATH_CONTEXTS = [ './/'.freeze ].freeze # :nodoc:
|
1566
|
+
IMPLIED_XPATH_CONTEXTS = [".//"].freeze
|
892
1567
|
|
893
|
-
def add_child_node_and_reparent_attrs
|
894
|
-
add_child_node
|
895
|
-
node.attribute_nodes.find_all { |a| a.name
|
1568
|
+
def add_child_node_and_reparent_attrs(node)
|
1569
|
+
add_child_node(node)
|
1570
|
+
node.attribute_nodes.find_all { |a| a.name.include?(":") }.each do |attr_node|
|
896
1571
|
attr_node.remove
|
897
1572
|
node[attr_node.name] = attr_node.value
|
898
1573
|
end
|
@@ -900,3 +1575,5 @@ Requires a Node, NodeSet or String argument, and cannot accept a #{data.class}.
|
|
900
1575
|
end
|
901
1576
|
end
|
902
1577
|
end
|
1578
|
+
|
1579
|
+
require_relative "node/save_options"
|