module Kramdown::Parser::Html::Parser
def handle_html_start_tag(line = nil) # :yields: el, closed, handle_body
body - and the end tag - need to be handled in case closed=false).
element is already closed, ie. contains no body; the third parameter specifies whether the
(first parameter is the created element; the second parameter is +true+ if the HTML
Does the common processing steps and then yields to the caller for further processing
Process the HTML start tag that has already be scanned/checked via @src.
def handle_html_start_tag(line = nil) # :yields: el, closed, handle_body name = @src[1] name.downcase! if HTML_ELEMENT[name.downcase] closed = !@src[4].nil? attrs = parse_html_attributes(@src[2], line, HTML_ELEMENT[name]) el = Element.new(:html_element, name, attrs, category: :block) el.options[:location] = line if line @tree.children << el if !closed && HTML_ELEMENTS_WITHOUT_BODY.include?(el.value) closed = true end if name == 'script' || name == 'style' handle_raw_html_tag(name) yield(el, false, false) else yield(el, closed, true) end end
def handle_raw_html_tag(name)
def handle_raw_html_tag(name) curpos = @src.pos if @src.scan_until(/(?=<\/#{name}\s*>)/mi) add_text(extract_string(curpos...@src.pos, @src), @tree.children.last, :raw) @src.scan(HTML_TAG_CLOSE_RE) else add_text(@src.rest, @tree.children.last, :raw) @src.terminate warning("Found no end tag for '#{name}' - auto-closing it") end end
def parse_html_attributes(str, line = nil, in_html_tag = true)
If the optional +in_html_tag+ parameter is set to +false+, attributes are not modified to
If the optional +line+ parameter is supplied, it is used in warning messages.
Parses the given string for HTML attributes and returns the resulting hash.
def parse_html_attributes(str, line = nil, in_html_tag = true) attrs = {} str.scan(HTML_ATTRIBUTE_RE).each do |attr, val, _sep, quoted_val| attr.downcase! if in_html_tag if attrs.key?(attr) warning("Duplicate HTML attribute '#{attr}' on line #{line || '?'} - overwriting previous one") end attrs[attr] = val || quoted_val || "" end attrs end
def parse_raw_html(el, &block)
When an HTML start tag is found, processing is deferred to #handle_html_start_tag,
element).
- The matching end tag for the element +el+ is found (only used if +el+ is an HTML
- The end of the document is reached.
Parsing continues until one of the following criteria are fulfilled:
Parse raw HTML from the current source position, storing the found elements in +el+.
def parse_raw_html(el, &block) @stack.push(@tree) @tree = el done = false while !@src.eos? && !done if (result = @src.scan_until(HTML_RAW_START)) add_text(result, @tree, :text) line = @src.current_line_number if (result = @src.scan(HTML_COMMENT_RE)) @tree.children << Element.new(:xml_comment, result, nil, category: :block, location: line) elsif (result = @src.scan(HTML_INSTRUCTION_RE)) @tree.children << Element.new(:xml_pi, result, nil, category: :block, location: line) elsif @src.scan(HTML_CDATA_RE) @tree.children << Element.new(:text, @src[1], nil, cdata: true, location: line) elsif @src.scan(HTML_TAG_RE) if method(:handle_html_start_tag).arity.abs >= 1 handle_html_start_tag(line, &block) else handle_html_start_tag(&block) # DEPRECATED: method needs to accept line number in 2.0 end elsif @src.scan(HTML_TAG_CLOSE_RE) if @tree.value == (HTML_ELEMENT[@tree.value] ? @src[1].downcase : @src[1]) done = true else add_text(@src.matched, @tree, :text) warning("Found invalidly used HTML closing tag for '#{@src[1]}' on " \ "line #{line} - ignoring it") end else add_text(@src.getch, @tree, :text) end else add_text(@src.rest, @tree, :text) @src.terminate if @tree.type == :html_element warning("Found no end tag for '#{@tree.value}' on line " \ "#{@tree.options[:location]} - auto-closing it") end done = true end end @tree = @stack.pop end