Module: Hpricot::Traverse
- Included in:
- Container::Trav, Leaf::Trav
- Defined in:
- lib/hpricot/traverse.rb,
lib/hpricot/modules.rb,
lib/hpricot/elements.rb,
lib/hpricot/traverse.rb
Overview
:startdoc:
Class Method Summary collapse
Instance Method Summary collapse
-
#after(html) ⇒ Object
Adds elements immediately after this element, contained in the
html
string. -
#at(expr) ⇒ Object
(also: #%)
Find the first matching node for the CSS or XPath
expr
string. -
#before(html) ⇒ Object
Adds elements immediately before this element, contained in the
html
string. -
#bogusetag? ⇒ Boolean
Is this object a stranded end tag?.
-
#children_of_type(tag_name) ⇒ Object
Find children of a given
tag_name
. - #clean_path(path) ⇒ Object
-
#comment? ⇒ Boolean
Is this object a comment?.
-
#css_path ⇒ Object
Builds a unique CSS string for this node, from the root of the document containing it.
-
#doc? ⇒ Boolean
Is this object the enclosing HTML or XML document?.
-
#doctype? ⇒ Boolean
Is this object a doctype tag?.
-
#elem? ⇒ Boolean
Is this object an HTML or XML element?.
- #get_subnode(*indexes) ⇒ Object
-
#inner_html ⇒ Object
(also: #innerHTML)
Builds an HTML string from the contents of this node.
-
#inner_html=(inner) ⇒ Object
(also: #innerHTML=)
Inserts new contents into the current node, based on the HTML contained in string
inner
. -
#inner_text ⇒ Object
(also: #innerText)
Builds a string from the text contained in this node.
-
#next_node ⇒ Object
Returns the node neighboring this node to the south: just below it.
- #node_position ⇒ Object
-
#nodes_at(*pos) ⇒ Object
Puts together an array of neighboring nodes based on their proximity to this node.
- #position ⇒ Object
-
#previous_node ⇒ Object
Returns to node neighboring this node to the north: just above it.
-
#procins? ⇒ Boolean
Is this object an XML processing instruction?.
-
#search(expr, &blk) ⇒ Object
(also: #/)
Searches this node for all elements matching the CSS or XPath
expr
. -
#swap(html) ⇒ Object
Replace this element and its contents with the nodes contained in the
html
string. -
#text? ⇒ Boolean
Is this object an HTML text node?.
-
#to_html ⇒ Object
(also: #to_s)
Builds an HTML string from this node and its contents.
-
#to_original_html ⇒ Object
Attempts to preserve the original HTML of the document, only outputing new tags for elements which have changed.
-
#to_plain_text ⇒ Object
Builds a string from the text contained in this node.
-
#traverse_element(*names, &block) ⇒ Object
traverse_element
traverses elements in the tree. -
#traverse_text(&block) ⇒ Object
traverse_text
traverses texts in the tree. -
#xmldecl? ⇒ Boolean
Is this object an XML declaration?.
-
#xpath ⇒ Object
Builds a unique XPath string for this node, from the root of the document containing it.
Class Method Details
.filter(tok, &blk) ⇒ Object
262 263 264 |
# File 'lib/hpricot/elements.rb', line 262 def self.filter(tok, &blk) define_method("filter[#{tok.is_a?(String) ? tok : tok.inspect}]", &blk) end |
Instance Method Details
#after(html) ⇒ Object
Adds elements immediately after this element, contained in the html
string.
76 77 78 |
# File 'lib/hpricot/traverse.rb', line 76 def after(html) parent.insert_after(Hpricot.make(html), self) end |
#at(expr) ⇒ Object Also known as: %
Find the first matching node for the CSS or XPath expr
string.
283 284 285 |
# File 'lib/hpricot/traverse.rb', line 283 def at(expr) search(expr).first end |
#before(html) ⇒ Object
Adds elements immediately before this element, contained in the html
string.
81 82 83 |
# File 'lib/hpricot/traverse.rb', line 81 def before(html) parent.insert_after(Hpricot.make(html), self) end |
#bogusetag? ⇒ Boolean
Is this object a stranded end tag?
21 |
# File 'lib/hpricot/traverse.rb', line 21 def bogusetag?() BogusETag::Trav === self end |
#children_of_type(tag_name) ⇒ Object
Find children of a given tag_name
.
ele.children_of_type('p')
#=> [...array of paragraphs...]
332 333 334 335 336 337 338 |
# File 'lib/hpricot/traverse.rb', line 332 def children_of_type(tag_name) if respond_to? :children children.find_all do |x| x.respond_to?(:pathname) && x.pathname == tag_name end end end |
#clean_path(path) ⇒ Object
148 149 150 |
# File 'lib/hpricot/traverse.rb', line 148 def clean_path(path) path.gsub(/^\s+|\s+$/, '') end |
#comment? ⇒ Boolean
Is this object a comment?
19 |
# File 'lib/hpricot/traverse.rb', line 19 def comment?() Comment::Trav === self end |
#css_path ⇒ Object
Builds a unique CSS string for this node, from the root of the document containing it.
171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 |
# File 'lib/hpricot/traverse.rb', line 171 def css_path if elem? and has_attribute? 'id' "##{get_attribute('id')}" else sim, i, id = 0, 0, 0 parent.children.each do |e| id = sim if e == self sim += 1 if e.pathname == self.pathname end p = parent.css_path p = p ? "#{p} > #{self.pathname}" : self.pathname p += ":nth(#{id})" if sim >= 2 p end end |
#doc? ⇒ Boolean
Is this object the enclosing HTML or XML document?
7 |
# File 'lib/hpricot/traverse.rb', line 7 def doc?() Doc::Trav === self end |
#doctype? ⇒ Boolean
Is this object a doctype tag?
15 |
# File 'lib/hpricot/traverse.rb', line 15 def doctype?() DocType::Trav === self end |
#elem? ⇒ Boolean
Is this object an HTML or XML element?
9 |
# File 'lib/hpricot/traverse.rb', line 9 def elem?() Elem::Trav === self end |
#get_subnode(*indexes) ⇒ Object
93 94 95 96 97 98 99 |
# File 'lib/hpricot/traverse.rb', line 93 def get_subnode(*indexes) n = self indexes.each {|index| n = n.get_subnode_internal(index) } n end |
#inner_html ⇒ Object Also known as: innerHTML
Builds an HTML string from the contents of this node.
119 120 121 122 123 |
# File 'lib/hpricot/traverse.rb', line 119 def inner_html if respond_to? :children children.map { |x| x.output("") }.join end end |
#inner_html=(inner) ⇒ Object Also known as: innerHTML=
Inserts new contents into the current node, based on the HTML contained in string inner
.
128 129 130 131 132 133 134 135 136 137 138 139 |
# File 'lib/hpricot/traverse.rb', line 128 def inner_html=(inner) altered! case inner when String, IO self.children = Hpricot.parse(inner).children when Array self.children = inner when nil self.children = [] end reparent self.children end |
#inner_text ⇒ Object Also known as: innerText
Builds a string from the text contained in this node. All HTML elements are removed.
111 112 113 114 115 |
# File 'lib/hpricot/traverse.rb', line 111 def inner_text if respond_to? :children children.map { |x| x.inner_text }.join end end |
#next_node ⇒ Object
Returns the node neighboring this node to the south: just below it. This method includes text nodes and comments and such.
62 63 64 65 |
# File 'lib/hpricot/traverse.rb', line 62 def next_node sib = parent.children sib[sib.index(self) + 1] if parent end |
#node_position ⇒ Object
187 188 189 |
# File 'lib/hpricot/traverse.rb', line 187 def node_position parent.children.index(self) end |
#nodes_at(*pos) ⇒ Object
Puts together an array of neighboring nodes based on their proximity to this node. So, for example, to get the next node, you could use nodes_at(1). Or, to get the previous node, use <tt>nodes_at(1)
.
This method also accepts ranges and sets of numbers.
ele.nodes_at(-3..-1, 1..3) # gets three nodes before and three after
ele.nodes_at(1, 5, 7) # gets three nodes at offsets below the current node
ele.nodes_at(0, 5..6) # the current node and two others
46 47 48 49 50 51 52 53 54 55 56 57 58 |
# File 'lib/hpricot/traverse.rb', line 46 def nodes_at(*pos) sib = parent.children i, si = 0, sib.index(self) Elements[* sib.select do |x| sel = case i - si when *pos true end i += 1 sel end ] end |
#position ⇒ Object
191 192 193 |
# File 'lib/hpricot/traverse.rb', line 191 def position parent.children_of_type(self.pathname).index(self) end |
#previous_node ⇒ Object
Returns to node neighboring this node to the north: just above it. This method includes text nodes and comments and such.
69 70 71 72 73 |
# File 'lib/hpricot/traverse.rb', line 69 def previous_node sib = parent.children x = sib.index(self) - 1 sib[x] if sib and x >= 0 end |
#procins? ⇒ Boolean
Is this object an XML processing instruction?
17 |
# File 'lib/hpricot/traverse.rb', line 17 def procins?() ProcIns::Trav === self end |
#search(expr, &blk) ⇒ Object Also known as: /
Searches this node for all elements matching the CSS or XPath expr
. Returns an Elements array containing the matching nodes. If blk
is given, it is used to iterate through the matching set.
199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 |
# File 'lib/hpricot/traverse.rb', line 199 def search(expr, &blk) last = nil nodes = [self] done = [] expr = expr.to_s hist = [] until expr.empty? expr = clean_path(expr) expr.gsub!(%r!^//!, '') case expr when %r!^/?\.\.! last = expr = $' nodes.map! { |node| node.parent } when %r!^[>/]! last = expr = $' nodes = Elements[*nodes.map { |node| node.children if node.respond_to? :children }.flatten.compact] when %r!^\+! last = expr = $' nodes.map! do |node| siblings = node.parent.children siblings[siblings.index(node)+1] end nodes.compact! when %r!^~! last = expr = $' nodes.map! do |node| siblings = node.parent.children siblings[(siblings.index(node)+1)..-1] end nodes.flatten! when %r!^[|,]! last = expr = " #$'" nodes.shift if nodes.first == self done += nodes nodes = [self] else m = expr.match(%r!^([#.]?)([a-z0-9\\*_-]*)!i).to_a after = $' mt = after[%r!:[a-z0-9\\*_-]+!i, 0] oop = false if mt and not (mt == ":not" or Traverse.method_defined? "filter[#{mt}]") after = $' m[2] += mt expr = after end if m[1] == '#' oid = get_element_by_id(m[2]) nodes = oid ? [oid] : [] expr = after else m[2] = "*" if after =~ /^\(\)/ || m[2] == "" || m[1] == "." ret = [] nodes.each do |node| case m[2] when '*' node.traverse_element { |n| ret << n } else if node.respond_to? :get_elements_by_tag_name ret += [*node.get_elements_by_tag_name(m[2])] - [*(node unless last)] end end end nodes = ret end last = nil end hist << expr break if hist[-1] == hist[-2] nodes, expr = Elements.filter(nodes, expr) end nodes = done + nodes.flatten.uniq if blk nodes.each(&blk) self else Elements[*nodes] end end |
#swap(html) ⇒ Object
Replace this element and its contents with the nodes contained in the html
string.
88 89 90 91 |
# File 'lib/hpricot/traverse.rb', line 88 def swap(html) parent.altered! parent.replace_child(self, Hpricot.make(html)) end |
#text? ⇒ Boolean
Is this object an HTML text node?
11 |
# File 'lib/hpricot/traverse.rb', line 11 def text?() Text::Trav === self end |
#to_html ⇒ Object Also known as: to_s
Builds an HTML string from this node and its contents. If you need to write to a stream, try calling output(io)
as a method on this object.
26 27 28 |
# File 'lib/hpricot/traverse.rb', line 26 def to_html output("") end |
#to_original_html ⇒ Object
Attempts to preserve the original HTML of the document, only outputing new tags for elements which have changed.
33 34 35 |
# File 'lib/hpricot/traverse.rb', line 33 def to_original_html output("", :preserve => true) end |
#to_plain_text ⇒ Object
Builds a string from the text contained in this node. All HTML elements are removed.
103 104 105 106 107 |
# File 'lib/hpricot/traverse.rb', line 103 def to_plain_text if respond_to? :children children.map { |x| x.to_plain_text }.join.strip.gsub(/\n{2,}/, "\n\n") end end |
#traverse_element(*names, &block) ⇒ Object
traverse_element
traverses elements in the tree. It yields elements in depth first order.
If names are empty, it yields all elements. If non-empty names are given, it should be list of universal names.
A nested element is yielded in depth first order as follows.
t = Hpricot('<a id=0><b><a id=1 /></b><c id=2 /></a>')
t.traverse_element("a", "c") {|e| p e}
# =>
{elem <a id="0"> {elem <b> {emptyelem <a id="1">} </b>} {emptyelem <c id="2">} </a>}
{emptyelem <a id="1">}
{emptyelem <c id="2">}
Universal names are specified as follows.
t = Hpricot(<<'End')
<html>
<meta name="robots" content="index,nofollow">
<meta name="author" content="Who am I?">
</html>
End
t.traverse_element("{http://www.w3.org/1999/xhtml}meta") {|e| p e}
# =>
{emptyelem <{http://www.w3.org/1999/xhtml}meta name="robots" content="index,nofollow">}
{emptyelem <{http://www.w3.org/1999/xhtml}meta name="author" content="Who am I?">}
316 317 318 319 320 321 322 323 324 325 |
# File 'lib/hpricot/traverse.rb', line 316 def traverse_element(*names, &block) # :yields: element if names.empty? traverse_all_element(&block) else name_set = {} names.each {|n| name_set[n] = true } traverse_some_element(name_set, &block) end nil end |
#traverse_text(&block) ⇒ Object
traverse_text
traverses texts in the tree
605 606 607 608 |
# File 'lib/hpricot/traverse.rb', line 605 def traverse_text(&block) # :yields: text traverse_text_internal(&block) nil end |
#xmldecl? ⇒ Boolean
Is this object an XML declaration?
13 |
# File 'lib/hpricot/traverse.rb', line 13 def xmldecl?() XMLDecl::Trav === self end |
#xpath ⇒ Object
Builds a unique XPath string for this node, from the root of the document containing it.
154 155 156 157 158 159 160 161 162 163 164 165 166 167 |
# File 'lib/hpricot/traverse.rb', line 154 def xpath if elem? and has_attribute? 'id' "//#{self.name}[@id='#{get_attribute('id')}']" else sim, id = 0, 0, 0 parent.children.each do |e| id = sim if e == self sim += 1 if e.pathname == self.pathname end p = File.join(parent.xpath, self.pathname) p += "[#{id+1}]" if sim >= 2 p end end |