each_child iterates over each child.
# File htree/traverse.rb, line 29 def each_child(&block) # :yields: child_node children.each(&block) nil end
each_child_with_index iterates over each child.
# File htree/traverse.rb, line 35 def each_child_with_index(&block) # :yields: child_node, index children.each_with_index(&block) nil end
each_hyperlink traverses hyperlinks such as HTML href attribute of A element.
It yields HTree::Text or HTree::Loc.
Note that each_hyperlink yields HTML href attribute of BASE element.
# File htree/traverse.rb, line 161 def each_hyperlink # :yields: text each_hyperlink_attribute {|elem, attr, hyperlink| yield hyperlink } end
each_hyperlink_uri traverses hyperlinks such as HTML href attribute of A element.
It yields HTree::Text (or HTree::Loc) and URI for each hyperlink.
The URI objects are created with a base URI which is given by HTML BASE element or the argument ((|base_uri|)). each_hyperlink_uri doesn't yields href of the BASE element.
# File htree/traverse.rb, line 138 def each_hyperlink_uri(base_uri=nil) # :yields: hyperlink, uri base_uri = URI.parse(base_uri) if String === base_uri links = [] each_hyperlink_attribute {|elem, attr, hyperlink| if %{\{http://www.w3.org/1999/xhtml\}(?:base)\z} =~ elem.name base_uri = URI.parse(hyperlink.to_s) else links << hyperlink end } if base_uri links.each {|hyperlink| yield hyperlink, base_uri + hyperlink.to_s } else links.each {|hyperlink| yield hyperlink, URI.parse(hyperlink.to_s) } end end
each_uri traverses hyperlinks such as HTML href attribute of A element.
It yields URI for each hyperlink.
The URI objects are created with a base URI which is given by HTML BASE element or the argument ((|base_uri|)).
# File htree/traverse.rb, line 174 def each_uri(base_uri=nil) # :yields: URI each_hyperlink_uri(base_uri) {|hyperlink, uri| yield uri } end
filter rebuilds the tree without some components.
node.filter {|descendant_node| predicate } -> node loc.filter {|descendant_loc| predicate } -> node
filter yields each node except top node. If given block returns false, corresponding node is dropped. If given block returns true, corresponding node is retained and inner nodes are examined.
filter returns an node. It doesn't return location object even if self is location object.
# File htree/traverse.rb, line 258 def filter(&block) subst = {} each_child_with_index {|descendant, i| if yield descendant if descendant.elem? subst[i] = descendant.filter(&block) else subst[i] = descendant end else subst[i] = nil end } to_node.subst_subnode(subst) end
find_element searches an element which universal name is specified by the arguments. It returns nil if not found.
# File htree/traverse.rb, line 43 def find_element(*names) traverse_element(*names) {|e| return e } nil end
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 = HTree('<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 = HTree(<<'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?">}
# File htree/traverse.rb, line 76 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
Generated with the Darkfish Rdoc Generator 2.