diff options
author | Piotr Sarnacki <drogus@gmail.com> | 2013-06-20 15:42:49 -0700 |
---|---|---|
committer | Piotr Sarnacki <drogus@gmail.com> | 2013-06-20 15:42:49 -0700 |
commit | a29f746398e7b0647885343e7f26d977dd251999 (patch) | |
tree | 1e2cd2ee1f8f31812c0acf71350ffe423ca8c5a9 /actionview/lib/action_view/vendor/html-scanner | |
parent | 7c69a829a311a31109939cff19b700b36b97d5c4 (diff) | |
parent | d6b1caa8f2011487c08b414605883f1f220d0aaa (diff) | |
download | rails-a29f746398e7b0647885343e7f26d977dd251999.tar.gz rails-a29f746398e7b0647885343e7f26d977dd251999.tar.bz2 rails-a29f746398e7b0647885343e7f26d977dd251999.zip |
Merge pull request #11032 from strzalek/extract-actionview
Extract ActionView to separate directory
Diffstat (limited to 'actionview/lib/action_view/vendor/html-scanner')
6 files changed, 1736 insertions, 0 deletions
diff --git a/actionview/lib/action_view/vendor/html-scanner/html/document.rb b/actionview/lib/action_view/vendor/html-scanner/html/document.rb new file mode 100644 index 0000000000..386820300a --- /dev/null +++ b/actionview/lib/action_view/vendor/html-scanner/html/document.rb @@ -0,0 +1,68 @@ +require 'html/tokenizer' +require 'html/node' +require 'html/selector' +require 'html/sanitizer' + +module HTML #:nodoc: + # A top-level HTML document. You give it a body of text, and it will parse that + # text into a tree of nodes. + class Document #:nodoc: + + # The root of the parsed document. + attr_reader :root + + # Create a new Document from the given text. + def initialize(text, strict=false, xml=false) + tokenizer = Tokenizer.new(text) + @root = Node.new(nil) + node_stack = [ @root ] + while token = tokenizer.next + node = Node.parse(node_stack.last, tokenizer.line, tokenizer.position, token, strict) + + node_stack.last.children << node unless node.tag? && node.closing == :close + if node.tag? + if node_stack.length > 1 && node.closing == :close + if node_stack.last.name == node.name + if node_stack.last.children.empty? + node_stack.last.children << Text.new(node_stack.last, node.line, node.position, "") + end + node_stack.pop + else + open_start = node_stack.last.position - 20 + open_start = 0 if open_start < 0 + close_start = node.position - 20 + close_start = 0 if close_start < 0 + msg = <<EOF.strip +ignoring attempt to close #{node_stack.last.name} with #{node.name} + opened at byte #{node_stack.last.position}, line #{node_stack.last.line} + closed at byte #{node.position}, line #{node.line} + attributes at open: #{node_stack.last.attributes.inspect} + text around open: #{text[open_start,40].inspect} + text around close: #{text[close_start,40].inspect} +EOF + strict ? raise(msg) : warn(msg) + end + elsif !node.childless?(xml) && node.closing != :close + node_stack.push node + end + end + end + end + + # Search the tree for (and return) the first node that matches the given + # conditions. The conditions are interpreted differently for different node + # types, see HTML::Text#find and HTML::Tag#find. + def find(conditions) + @root.find(conditions) + end + + # Search the tree for (and return) all nodes that match the given + # conditions. The conditions are interpreted differently for different node + # types, see HTML::Text#find and HTML::Tag#find. + def find_all(conditions) + @root.find_all(conditions) + end + + end + +end diff --git a/actionview/lib/action_view/vendor/html-scanner/html/node.rb b/actionview/lib/action_view/vendor/html-scanner/html/node.rb new file mode 100644 index 0000000000..7e7cd4f7b6 --- /dev/null +++ b/actionview/lib/action_view/vendor/html-scanner/html/node.rb @@ -0,0 +1,532 @@ +require 'strscan' + +module HTML #:nodoc: + + class Conditions < Hash #:nodoc: + def initialize(hash) + super() + hash = { :content => hash } unless Hash === hash + hash = keys_to_symbols(hash) + hash.each do |k,v| + case k + when :tag, :content then + # keys are valid, and require no further processing + when :attributes then + hash[k] = keys_to_strings(v) + when :parent, :child, :ancestor, :descendant, :sibling, :before, + :after + hash[k] = Conditions.new(v) + when :children + hash[k] = v = keys_to_symbols(v) + v.each do |key,value| + case key + when :count, :greater_than, :less_than + # keys are valid, and require no further processing + when :only + v[key] = Conditions.new(value) + else + raise "illegal key #{key.inspect} => #{value.inspect}" + end + end + else + raise "illegal key #{k.inspect} => #{v.inspect}" + end + end + update hash + end + + private + + def keys_to_strings(hash) + Hash[hash.keys.map {|k| [k.to_s, hash[k]]}] + end + + def keys_to_symbols(hash) + Hash[hash.keys.map do |k| + raise "illegal key #{k.inspect}" unless k.respond_to?(:to_sym) + [k.to_sym, hash[k]] + end] + end + end + + # The base class of all nodes, textual and otherwise, in an HTML document. + class Node #:nodoc: + # The array of children of this node. Not all nodes have children. + attr_reader :children + + # The parent node of this node. All nodes have a parent, except for the + # root node. + attr_reader :parent + + # The line number of the input where this node was begun + attr_reader :line + + # The byte position in the input where this node was begun + attr_reader :position + + # Create a new node as a child of the given parent. + def initialize(parent, line=0, pos=0) + @parent = parent + @children = [] + @line, @position = line, pos + end + + # Return a textual representation of the node. + def to_s + @children.join() + end + + # Return false (subclasses must override this to provide specific matching + # behavior.) +conditions+ may be of any type. + def match(conditions) + false + end + + # Search the children of this node for the first node for which #find + # returns non +nil+. Returns the result of the #find call that succeeded. + def find(conditions) + conditions = validate_conditions(conditions) + @children.each do |child| + node = child.find(conditions) + return node if node + end + nil + end + + # Search for all nodes that match the given conditions, and return them + # as an array. + def find_all(conditions) + conditions = validate_conditions(conditions) + + matches = [] + matches << self if match(conditions) + @children.each do |child| + matches.concat child.find_all(conditions) + end + matches + end + + # Returns +false+. Subclasses may override this if they define a kind of + # tag. + def tag? + false + end + + def validate_conditions(conditions) + Conditions === conditions ? conditions : Conditions.new(conditions) + end + + def ==(node) + return false unless self.class == node.class && children.size == node.children.size + + equivalent = true + + children.size.times do |i| + equivalent &&= children[i] == node.children[i] + end + + equivalent + end + + class <<self + def parse(parent, line, pos, content, strict=true) + if content !~ /^<\S/ + Text.new(parent, line, pos, content) + else + scanner = StringScanner.new(content) + + unless scanner.skip(/</) + if strict + raise "expected <" + else + return Text.new(parent, line, pos, content) + end + end + + if scanner.skip(/!\[CDATA\[/) + unless scanner.skip_until(/\]\]>/) + if strict + raise "expected ]]> (got #{scanner.rest.inspect} for #{content})" + else + scanner.skip_until(/\Z/) + end + end + + return CDATA.new(parent, line, pos, scanner.pre_match.gsub(/<!\[CDATA\[/, '')) + end + + closing = ( scanner.scan(/\//) ? :close : nil ) + return Text.new(parent, line, pos, content) unless name = scanner.scan(/[^\s!>\/]+/) + name.downcase! + + unless closing + scanner.skip(/\s*/) + attributes = {} + while attr = scanner.scan(/[-\w:]+/) + value = true + if scanner.scan(/\s*=\s*/) + if delim = scanner.scan(/['"]/) + value = "" + while text = scanner.scan(/[^#{delim}\\]+|./) + case text + when "\\" then + value << text + break if scanner.eos? + value << scanner.getch + when delim + break + else value << text + end + end + else + value = scanner.scan(/[^\s>\/]+/) + end + end + attributes[attr.downcase] = value + scanner.skip(/\s*/) + end + + closing = ( scanner.scan(/\//) ? :self : nil ) + end + + unless scanner.scan(/\s*>/) + if strict + raise "expected > (got #{scanner.rest.inspect} for #{content}, #{attributes.inspect})" + else + # throw away all text until we find what we're looking for + scanner.skip_until(/>/) or scanner.terminate + end + end + + Tag.new(parent, line, pos, name, attributes, closing) + end + end + end + end + + # A node that represents text, rather than markup. + class Text < Node #:nodoc: + + attr_reader :content + + # Creates a new text node as a child of the given parent, with the given + # content. + def initialize(parent, line, pos, content) + super(parent, line, pos) + @content = content + end + + # Returns the content of this node. + def to_s + @content + end + + # Returns +self+ if this node meets the given conditions. Text nodes support + # conditions of the following kinds: + # + # * if +conditions+ is a string, it must be a substring of the node's + # content + # * if +conditions+ is a regular expression, it must match the node's + # content + # * if +conditions+ is a hash, it must contain a <tt>:content</tt> key that + # is either a string or a regexp, and which is interpreted as described + # above. + def find(conditions) + match(conditions) && self + end + + # Returns non-+nil+ if this node meets the given conditions, or +nil+ + # otherwise. See the discussion of #find for the valid conditions. + def match(conditions) + case conditions + when String + @content == conditions + when Regexp + @content =~ conditions + when Hash + conditions = validate_conditions(conditions) + + # Text nodes only have :content, :parent, :ancestor + unless (conditions.keys - [:content, :parent, :ancestor]).empty? + return false + end + + match(conditions[:content]) + else + nil + end + end + + def ==(node) + return false unless super + content == node.content + end + end + + # A CDATA node is simply a text node with a specialized way of displaying + # itself. + class CDATA < Text #:nodoc: + def to_s + "<![CDATA[#{super}]]>" + end + end + + # A Tag is any node that represents markup. It may be an opening tag, a + # closing tag, or a self-closing tag. It has a name, and may have a hash of + # attributes. + class Tag < Node #:nodoc: + + # Either +nil+, <tt>:close</tt>, or <tt>:self</tt> + attr_reader :closing + + # Either +nil+, or a hash of attributes for this node. + attr_reader :attributes + + # The name of this tag. + attr_reader :name + + # Create a new node as a child of the given parent, using the given content + # to describe the node. It will be parsed and the node name, attributes and + # closing status extracted. + def initialize(parent, line, pos, name, attributes, closing) + super(parent, line, pos) + @name = name + @attributes = attributes + @closing = closing + end + + # A convenience for obtaining an attribute of the node. Returns +nil+ if + # the node has no attributes. + def [](attr) + @attributes ? @attributes[attr] : nil + end + + # Returns non-+nil+ if this tag can contain child nodes. + def childless?(xml = false) + return false if xml && @closing.nil? + !@closing.nil? || + @name =~ /^(img|br|hr|link|meta|area|base|basefont| + col|frame|input|isindex|param)$/ox + end + + # Returns a textual representation of the node + def to_s + if @closing == :close + "</#{@name}>" + else + s = "<#{@name}" + @attributes.each do |k,v| + s << " #{k}" + s << "=\"#{v}\"" if String === v + end + s << " /" if @closing == :self + s << ">" + @children.each { |child| s << child.to_s } + s << "</#{@name}>" if @closing != :self && !@children.empty? + s + end + end + + # If either the node or any of its children meet the given conditions, the + # matching node is returned. Otherwise, +nil+ is returned. (See the + # description of the valid conditions in the +match+ method.) + def find(conditions) + match(conditions) && self || super + end + + # Returns +true+, indicating that this node represents an HTML tag. + def tag? + true + end + + # Returns +true+ if the node meets any of the given conditions. The + # +conditions+ parameter must be a hash of any of the following keys + # (all are optional): + # + # * <tt>:tag</tt>: the node name must match the corresponding value + # * <tt>:attributes</tt>: a hash. The node's values must match the + # corresponding values in the hash. + # * <tt>:parent</tt>: a hash. The node's parent must match the + # corresponding hash. + # * <tt>:child</tt>: a hash. At least one of the node's immediate children + # must meet the criteria described by the hash. + # * <tt>:ancestor</tt>: a hash. At least one of the node's ancestors must + # meet the criteria described by the hash. + # * <tt>:descendant</tt>: a hash. At least one of the node's descendants + # must meet the criteria described by the hash. + # * <tt>:sibling</tt>: a hash. At least one of the node's siblings must + # meet the criteria described by the hash. + # * <tt>:after</tt>: a hash. The node must be after any sibling meeting + # the criteria described by the hash, and at least one sibling must match. + # * <tt>:before</tt>: a hash. The node must be before any sibling meeting + # the criteria described by the hash, and at least one sibling must match. + # * <tt>:children</tt>: a hash, for counting children of a node. Accepts the + # keys: + # ** <tt>:count</tt>: either a number or a range which must equal (or + # include) the number of children that match. + # ** <tt>:less_than</tt>: the number of matching children must be less than + # this number. + # ** <tt>:greater_than</tt>: the number of matching children must be + # greater than this number. + # ** <tt>:only</tt>: another hash consisting of the keys to use + # to match on the children, and only matching children will be + # counted. + # + # Conditions are matched using the following algorithm: + # + # * if the condition is a string, it must be a substring of the value. + # * if the condition is a regexp, it must match the value. + # * if the condition is a number, the value must match number.to_s. + # * if the condition is +true+, the value must not be +nil+. + # * if the condition is +false+ or +nil+, the value must be +nil+. + # + # Usage: + # + # # test if the node is a "span" tag + # node.match tag: "span" + # + # # test if the node's parent is a "div" + # node.match parent: { tag: "div" } + # + # # test if any of the node's ancestors are "table" tags + # node.match ancestor: { tag: "table" } + # + # # test if any of the node's immediate children are "em" tags + # node.match child: { tag: "em" } + # + # # test if any of the node's descendants are "strong" tags + # node.match descendant: { tag: "strong" } + # + # # test if the node has between 2 and 4 span tags as immediate children + # node.match children: { count: 2..4, only: { tag: "span" } } + # + # # get funky: test to see if the node is a "div", has a "ul" ancestor + # # and an "li" parent (with "class" = "enum"), and whether or not it has + # # a "span" descendant that contains # text matching /hello world/: + # node.match tag: "div", + # ancestor: { tag: "ul" }, + # parent: { tag: "li", + # attributes: { class: "enum" } }, + # descendant: { tag: "span", + # child: /hello world/ } + def match(conditions) + conditions = validate_conditions(conditions) + # check content of child nodes + if conditions[:content] + if children.empty? + return false unless match_condition("", conditions[:content]) + else + return false unless children.find { |child| child.match(conditions[:content]) } + end + end + + # test the name + return false unless match_condition(@name, conditions[:tag]) if conditions[:tag] + + # test attributes + (conditions[:attributes] || {}).each do |key, value| + return false unless match_condition(self[key], value) + end + + # test parent + return false unless parent.match(conditions[:parent]) if conditions[:parent] + + # test children + return false unless children.find { |child| child.match(conditions[:child]) } if conditions[:child] + + # test ancestors + if conditions[:ancestor] + return false unless catch :found do + p = self + throw :found, true if p.match(conditions[:ancestor]) while p = p.parent + end + end + + # test descendants + if conditions[:descendant] + return false unless children.find do |child| + # test the child + child.match(conditions[:descendant]) || + # test the child's descendants + child.match(:descendant => conditions[:descendant]) + end + end + + # count children + if opts = conditions[:children] + matches = children.select do |c| + (c.kind_of?(HTML::Tag) and (c.closing == :self or ! c.childless?)) + end + + matches = matches.select { |c| c.match(opts[:only]) } if opts[:only] + opts.each do |key, value| + next if key == :only + case key + when :count + if Integer === value + return false if matches.length != value + else + return false unless value.include?(matches.length) + end + when :less_than + return false unless matches.length < value + when :greater_than + return false unless matches.length > value + else raise "unknown count condition #{key}" + end + end + end + + # test siblings + if conditions[:sibling] || conditions[:before] || conditions[:after] + siblings = parent ? parent.children : [] + self_index = siblings.index(self) + + if conditions[:sibling] + return false unless siblings.detect do |s| + s != self && s.match(conditions[:sibling]) + end + end + + if conditions[:before] + return false unless siblings[self_index+1..-1].detect do |s| + s != self && s.match(conditions[:before]) + end + end + + if conditions[:after] + return false unless siblings[0,self_index].detect do |s| + s != self && s.match(conditions[:after]) + end + end + end + + true + end + + def ==(node) + return false unless super + return false unless closing == node.closing && self.name == node.name + attributes == node.attributes + end + + private + # Match the given value to the given condition. + def match_condition(value, condition) + case condition + when String + value && value == condition + when Regexp + value && value.match(condition) + when Numeric + value == condition.to_s + when true + !value.nil? + when false, nil + value.nil? + else + false + end + end + end +end diff --git a/actionview/lib/action_view/vendor/html-scanner/html/sanitizer.rb b/actionview/lib/action_view/vendor/html-scanner/html/sanitizer.rb new file mode 100644 index 0000000000..30b6b8b141 --- /dev/null +++ b/actionview/lib/action_view/vendor/html-scanner/html/sanitizer.rb @@ -0,0 +1,188 @@ +require 'set' +require 'cgi' +require 'active_support/core_ext/class/attribute_accessors' + +module HTML + class Sanitizer + def sanitize(text, options = {}) + validate_options(options) + return text unless sanitizeable?(text) + tokenize(text, options).join + end + + def sanitizeable?(text) + !(text.nil? || text.empty? || !text.index("<")) + end + + protected + def tokenize(text, options) + tokenizer = HTML::Tokenizer.new(text) + result = [] + while token = tokenizer.next + node = Node.parse(nil, 0, 0, token, false) + process_node node, result, options + end + result + end + + def process_node(node, result, options) + result << node.to_s + end + + def validate_options(options) + if options[:tags] && !options[:tags].is_a?(Enumerable) + raise ArgumentError, "You should pass :tags as an Enumerable" + end + + if options[:attributes] && !options[:attributes].is_a?(Enumerable) + raise ArgumentError, "You should pass :attributes as an Enumerable" + end + end + end + + class FullSanitizer < Sanitizer + def sanitize(text, options = {}) + result = super + # strip any comments, and if they have a newline at the end (ie. line with + # only a comment) strip that too + result = result.gsub(/<!--(.*?)-->[\n]?/m, "") if (result && result =~ /<!--(.*?)-->[\n]?/m) + # Recurse - handle all dirty nested tags + result == text ? result : sanitize(result, options) + end + + def process_node(node, result, options) + result << node.to_s if node.class == HTML::Text + end + end + + class LinkSanitizer < FullSanitizer + cattr_accessor :included_tags, :instance_writer => false + self.included_tags = Set.new(%w(a href)) + + def sanitizeable?(text) + !(text.nil? || text.empty? || !((text.index("<a") || text.index("<href")) && text.index(">"))) + end + + protected + def process_node(node, result, options) + result << node.to_s unless node.is_a?(HTML::Tag) && included_tags.include?(node.name) + end + end + + class WhiteListSanitizer < Sanitizer + [:protocol_separator, :uri_attributes, :allowed_attributes, :allowed_tags, :allowed_protocols, :bad_tags, + :allowed_css_properties, :allowed_css_keywords, :shorthand_css_properties].each do |attr| + class_attribute attr, :instance_writer => false + end + + # A regular expression of the valid characters used to separate protocols like + # the ':' in 'http://foo.com' + self.protocol_separator = /:|(�*58)|(p)|(�*3a)|(%|%)3A/i + + # Specifies a Set of HTML attributes that can have URIs. + self.uri_attributes = Set.new(%w(href src cite action longdesc xlink:href lowsrc)) + + # Specifies a Set of 'bad' tags that the #sanitize helper will remove completely, as opposed + # to just escaping harmless tags like <font> + self.bad_tags = Set.new(%w(script)) + + # Specifies the default Set of tags that the #sanitize helper will allow unscathed. + self.allowed_tags = Set.new(%w(strong em b i p code pre tt samp kbd var sub + sup dfn cite big small address hr br div span h1 h2 h3 h4 h5 h6 ul ol li dl dt dd abbr + acronym a img blockquote del ins)) + + # Specifies the default Set of html attributes that the #sanitize helper will leave + # in the allowed tag. + self.allowed_attributes = Set.new(%w(href src width height alt cite datetime title class name xml:lang abbr)) + + # Specifies the default Set of acceptable css properties that #sanitize and #sanitize_css will accept. + self.allowed_protocols = Set.new(%w(ed2k ftp http https irc mailto news gopher nntp telnet webcal xmpp callto + feed svn urn aim rsync tag ssh sftp rtsp afs)) + + # Specifies the default Set of acceptable css properties that #sanitize and #sanitize_css will accept. + self.allowed_css_properties = Set.new(%w(azimuth background-color border-bottom-color border-collapse + border-color border-left-color border-right-color border-top-color clear color cursor direction display + elevation float font font-family font-size font-style font-variant font-weight height letter-spacing line-height + overflow pause pause-after pause-before pitch pitch-range richness speak speak-header speak-numeral speak-punctuation + speech-rate stress text-align text-decoration text-indent unicode-bidi vertical-align voice-family volume white-space + width)) + + # Specifies the default Set of acceptable css keywords that #sanitize and #sanitize_css will accept. + self.allowed_css_keywords = Set.new(%w(auto aqua black block blue bold both bottom brown center + collapse dashed dotted fuchsia gray green !important italic left lime maroon medium none navy normal + nowrap olive pointer purple red right solid silver teal top transparent underline white yellow)) + + # Specifies the default Set of allowed shorthand css properties for the #sanitize and #sanitize_css helpers. + self.shorthand_css_properties = Set.new(%w(background border margin padding)) + + # Sanitizes a block of css code. Used by #sanitize when it comes across a style attribute + def sanitize_css(style) + # disallow urls + style = style.to_s.gsub(/url\s*\(\s*[^\s)]+?\s*\)\s*/, ' ') + + # gauntlet + if style !~ /\A([:,;#%.\sa-zA-Z0-9!]|\w-\w|\'[\s\w]+\'|\"[\s\w]+\"|\([\d,\s]+\))*\z/ || + style !~ /\A(\s*[-\w]+\s*:\s*[^:;]*(;|$)\s*)*\z/ + return '' + end + + clean = [] + style.scan(/([-\w]+)\s*:\s*([^:;]*)/) do |prop,val| + if allowed_css_properties.include?(prop.downcase) + clean << prop + ': ' + val + ';' + elsif shorthand_css_properties.include?(prop.split('-')[0].downcase) + unless val.split().any? do |keyword| + !allowed_css_keywords.include?(keyword) && + keyword !~ /\A(#[0-9a-f]+|rgb\(\d+%?,\d*%?,?\d*%?\)?|\d{0,2}\.?\d{0,2}(cm|em|ex|in|mm|pc|pt|px|%|,|\))?)\z/ + end + clean << prop + ': ' + val + ';' + end + end + end + clean.join(' ') + end + + protected + def tokenize(text, options) + options[:parent] = [] + options[:attributes] ||= allowed_attributes + options[:tags] ||= allowed_tags + super + end + + def process_node(node, result, options) + result << case node + when HTML::Tag + if node.closing == :close + options[:parent].shift + else + options[:parent].unshift node.name + end + + process_attributes_for node, options + + options[:tags].include?(node.name) ? node : nil + else + bad_tags.include?(options[:parent].first) ? nil : node.to_s.gsub(/</, "<") + end + end + + def process_attributes_for(node, options) + return unless node.attributes + node.attributes.keys.each do |attr_name| + value = node.attributes[attr_name].to_s + + if !options[:attributes].include?(attr_name) || contains_bad_protocols?(attr_name, value) + node.attributes.delete(attr_name) + else + node.attributes[attr_name] = attr_name == 'style' ? sanitize_css(value) : CGI::escapeHTML(CGI::unescapeHTML(value)) + end + end + end + + def contains_bad_protocols?(attr_name, value) + uri_attributes.include?(attr_name) && + (value =~ /(^[^\/:]*):|(�*58)|(p)|(�*3a)|(%|%)3A/i && !allowed_protocols.include?(value.split(protocol_separator).first.downcase.strip)) + end + end +end diff --git a/actionview/lib/action_view/vendor/html-scanner/html/selector.rb b/actionview/lib/action_view/vendor/html-scanner/html/selector.rb new file mode 100644 index 0000000000..7f8609c408 --- /dev/null +++ b/actionview/lib/action_view/vendor/html-scanner/html/selector.rb @@ -0,0 +1,830 @@ +#-- +# Copyright (c) 2006 Assaf Arkin (http://labnotes.org) +# Under MIT and/or CC By license. +#++ + +module HTML + + # Selects HTML elements using CSS 2 selectors. + # + # The +Selector+ class uses CSS selector expressions to match and select + # HTML elements. + # + # For example: + # selector = HTML::Selector.new "form.login[action=/login]" + # creates a new selector that matches any +form+ element with the class + # +login+ and an attribute +action+ with the value <tt>/login</tt>. + # + # === Matching Elements + # + # Use the #match method to determine if an element matches the selector. + # + # For simple selectors, the method returns an array with that element, + # or +nil+ if the element does not match. For complex selectors (see below) + # the method returns an array with all matched elements, of +nil+ if no + # match found. + # + # For example: + # if selector.match(element) + # puts "Element is a login form" + # end + # + # === Selecting Elements + # + # Use the #select method to select all matching elements starting with + # one element and going through all children in depth-first order. + # + # This method returns an array of all matching elements, an empty array + # if no match is found + # + # For example: + # selector = HTML::Selector.new "input[type=text]" + # matches = selector.select(element) + # matches.each do |match| + # puts "Found text field with name #{match.attributes['name']}" + # end + # + # === Expressions + # + # Selectors can match elements using any of the following criteria: + # * <tt>name</tt> -- Match an element based on its name (tag name). + # For example, <tt>p</tt> to match a paragraph. You can use <tt>*</tt> + # to match any element. + # * <tt>#</tt><tt>id</tt> -- Match an element based on its identifier (the + # <tt>id</tt> attribute). For example, <tt>#</tt><tt>page</tt>. + # * <tt>.class</tt> -- Match an element based on its class name, all + # class names if more than one specified. + # * <tt>[attr]</tt> -- Match an element that has the specified attribute. + # * <tt>[attr=value]</tt> -- Match an element that has the specified + # attribute and value. (More operators are supported see below) + # * <tt>:pseudo-class</tt> -- Match an element based on a pseudo class, + # such as <tt>:nth-child</tt> and <tt>:empty</tt>. + # * <tt>:not(expr)</tt> -- Match an element that does not match the + # negation expression. + # + # When using a combination of the above, the element name comes first + # followed by identifier, class names, attributes, pseudo classes and + # negation in any order. Do not separate these parts with spaces! + # Space separation is used for descendant selectors. + # + # For example: + # selector = HTML::Selector.new "form.login[action=/login]" + # The matched element must be of type +form+ and have the class +login+. + # It may have other classes, but the class +login+ is required to match. + # It must also have an attribute called +action+ with the value + # <tt>/login</tt>. + # + # This selector will match the following element: + # <form class="login form" method="post" action="/login"> + # but will not match the element: + # <form method="post" action="/logout"> + # + # === Attribute Values + # + # Several operators are supported for matching attributes: + # * <tt>name</tt> -- The element must have an attribute with that name. + # * <tt>name=value</tt> -- The element must have an attribute with that + # name and value. + # * <tt>name^=value</tt> -- The attribute value must start with the + # specified value. + # * <tt>name$=value</tt> -- The attribute value must end with the + # specified value. + # * <tt>name*=value</tt> -- The attribute value must contain the + # specified value. + # * <tt>name~=word</tt> -- The attribute value must contain the specified + # word (space separated). + # * <tt>name|=word</tt> -- The attribute value must start with specified + # word. + # + # For example, the following two selectors match the same element: + # #my_id + # [id=my_id] + # and so do the following two selectors: + # .my_class + # [class~=my_class] + # + # === Alternatives, siblings, children + # + # Complex selectors use a combination of expressions to match elements: + # * <tt>expr1 expr2</tt> -- Match any element against the second expression + # if it has some parent element that matches the first expression. + # * <tt>expr1 > expr2</tt> -- Match any element against the second expression + # if it is the child of an element that matches the first expression. + # * <tt>expr1 + expr2</tt> -- Match any element against the second expression + # if it immediately follows an element that matches the first expression. + # * <tt>expr1 ~ expr2</tt> -- Match any element against the second expression + # that comes after an element that matches the first expression. + # * <tt>expr1, expr2</tt> -- Match any element against the first expression, + # or against the second expression. + # + # Since children and sibling selectors may match more than one element given + # the first element, the #match method may return more than one match. + # + # === Pseudo classes + # + # Pseudo classes were introduced in CSS 3. They are most often used to select + # elements in a given position: + # * <tt>:root</tt> -- Match the element only if it is the root element + # (no parent element). + # * <tt>:empty</tt> -- Match the element only if it has no child elements, + # and no text content. + # * <tt>:content(string)</tt> -- Match the element only if it has <tt>string</tt> + # as its text content (ignoring leading and trailing whitespace). + # * <tt>:only-child</tt> -- Match the element if it is the only child (element) + # of its parent element. + # * <tt>:only-of-type</tt> -- Match the element if it is the only child (element) + # of its parent element and its type. + # * <tt>:first-child</tt> -- Match the element if it is the first child (element) + # of its parent element. + # * <tt>:first-of-type</tt> -- Match the element if it is the first child (element) + # of its parent element of its type. + # * <tt>:last-child</tt> -- Match the element if it is the last child (element) + # of its parent element. + # * <tt>:last-of-type</tt> -- Match the element if it is the last child (element) + # of its parent element of its type. + # * <tt>:nth-child(b)</tt> -- Match the element if it is the b-th child (element) + # of its parent element. The value <tt>b</tt> specifies its index, starting with 1. + # * <tt>:nth-child(an+b)</tt> -- Match the element if it is the b-th child (element) + # in each group of <tt>a</tt> child elements of its parent element. + # * <tt>:nth-child(-an+b)</tt> -- Match the element if it is the first child (element) + # in each group of <tt>a</tt> child elements, up to the first <tt>b</tt> child + # elements of its parent element. + # * <tt>:nth-child(odd)</tt> -- Match element in the odd position (i.e. first, third). + # Same as <tt>:nth-child(2n+1)</tt>. + # * <tt>:nth-child(even)</tt> -- Match element in the even position (i.e. second, + # fourth). Same as <tt>:nth-child(2n+2)</tt>. + # * <tt>:nth-of-type(..)</tt> -- As above, but only counts elements of its type. + # * <tt>:nth-last-child(..)</tt> -- As above, but counts from the last child. + # * <tt>:nth-last-of-type(..)</tt> -- As above, but counts from the last child and + # only elements of its type. + # * <tt>:not(selector)</tt> -- Match the element only if the element does not + # match the simple selector. + # + # As you can see, <tt>:nth-child</tt> pseudo class and its variant can get quite + # tricky and the CSS specification doesn't do a much better job explaining it. + # But after reading the examples and trying a few combinations, it's easy to + # figure out. + # + # For example: + # table tr:nth-child(odd) + # Selects every second row in the table starting with the first one. + # + # div p:nth-child(4) + # Selects the fourth paragraph in the +div+, but not if the +div+ contains + # other elements, since those are also counted. + # + # div p:nth-of-type(4) + # Selects the fourth paragraph in the +div+, counting only paragraphs, and + # ignoring all other elements. + # + # div p:nth-of-type(-n+4) + # Selects the first four paragraphs, ignoring all others. + # + # And you can always select an element that matches one set of rules but + # not another using <tt>:not</tt>. For example: + # p:not(.post) + # Matches all paragraphs that do not have the class <tt>.post</tt>. + # + # === Substitution Values + # + # You can use substitution with identifiers, class names and element values. + # A substitution takes the form of a question mark (<tt>?</tt>) and uses the + # next value in the argument list following the CSS expression. + # + # The substitution value may be a string or a regular expression. All other + # values are converted to strings. + # + # For example: + # selector = HTML::Selector.new "#?", /^\d+$/ + # matches any element whose identifier consists of one or more digits. + # + # See http://www.w3.org/TR/css3-selectors/ + class Selector + + + # An invalid selector. + class InvalidSelectorError < StandardError #:nodoc: + end + + + class << self + + # :call-seq: + # Selector.for_class(cls) => selector + # + # Creates a new selector for the given class name. + def for_class(cls) + self.new([".?", cls]) + end + + + # :call-seq: + # Selector.for_id(id) => selector + # + # Creates a new selector for the given id. + def for_id(id) + self.new(["#?", id]) + end + + end + + + # :call-seq: + # Selector.new(string, [values ...]) => selector + # + # Creates a new selector from a CSS 2 selector expression. + # + # The first argument is the selector expression. All other arguments + # are used for value substitution. + # + # Throws InvalidSelectorError is the selector expression is invalid. + def initialize(selector, *values) + raise ArgumentError, "CSS expression cannot be empty" if selector.empty? + @source = "" + values = values[0] if values.size == 1 && values[0].is_a?(Array) + + # We need a copy to determine if we failed to parse, and also + # preserve the original pass by-ref statement. + statement = selector.strip.dup + + # Create a simple selector, along with negation. + simple_selector(statement, values).each { |name, value| instance_variable_set("@#{name}", value) } + + @alternates = [] + @depends = nil + + # Alternative selector. + if statement.sub!(/^\s*,\s*/, "") + second = Selector.new(statement, values) + @alternates << second + # If there are alternate selectors, we group them in the top selector. + if alternates = second.instance_variable_get(:@alternates) + second.instance_variable_set(:@alternates, []) + @alternates.concat alternates + end + @source << " , " << second.to_s + # Sibling selector: create a dependency into second selector that will + # match element immediately following this one. + elsif statement.sub!(/^\s*\+\s*/, "") + second = next_selector(statement, values) + @depends = lambda do |element, first| + if element = next_element(element) + second.match(element, first) + end + end + @source << " + " << second.to_s + # Adjacent selector: create a dependency into second selector that will + # match all elements following this one. + elsif statement.sub!(/^\s*~\s*/, "") + second = next_selector(statement, values) + @depends = lambda do |element, first| + matches = [] + while element = next_element(element) + if subset = second.match(element, first) + if first && !subset.empty? + matches << subset.first + break + else + matches.concat subset + end + end + end + matches.empty? ? nil : matches + end + @source << " ~ " << second.to_s + # Child selector: create a dependency into second selector that will + # match a child element of this one. + elsif statement.sub!(/^\s*>\s*/, "") + second = next_selector(statement, values) + @depends = lambda do |element, first| + matches = [] + element.children.each do |child| + if child.tag? && subset = second.match(child, first) + if first && !subset.empty? + matches << subset.first + break + else + matches.concat subset + end + end + end + matches.empty? ? nil : matches + end + @source << " > " << second.to_s + # Descendant selector: create a dependency into second selector that + # will match all descendant elements of this one. Note, + elsif statement =~ /^\s+\S+/ && statement != selector + second = next_selector(statement, values) + @depends = lambda do |element, first| + matches = [] + stack = element.children.reverse + while node = stack.pop + next unless node.tag? + if subset = second.match(node, first) + if first && !subset.empty? + matches << subset.first + break + else + matches.concat subset + end + elsif children = node.children + stack.concat children.reverse + end + end + matches.empty? ? nil : matches + end + @source << " " << second.to_s + else + # The last selector is where we check that we parsed + # all the parts. + unless statement.empty? || statement.strip.empty? + raise ArgumentError, "Invalid selector: #{statement}" + end + end + end + + + # :call-seq: + # match(element, first?) => array or nil + # + # Matches an element against the selector. + # + # For a simple selector this method returns an array with the + # element if the element matches, nil otherwise. + # + # For a complex selector (sibling and descendant) this method + # returns an array with all matching elements, nil if no match is + # found. + # + # Use +first_only=true+ if you are only interested in the first element. + # + # For example: + # if selector.match(element) + # puts "Element is a login form" + # end + def match(element, first_only = false) + # Match element if no element name or element name same as element name + if matched = (!@tag_name || @tag_name == element.name) + # No match if one of the attribute matches failed + for attr in @attributes + if element.attributes[attr[0]] !~ attr[1] + matched = false + break + end + end + end + + # Pseudo class matches (nth-child, empty, etc). + if matched + for pseudo in @pseudo + unless pseudo.call(element) + matched = false + break + end + end + end + + # Negation. Same rules as above, but we fail if a match is made. + if matched && @negation + for negation in @negation + if negation[:tag_name] == element.name + matched = false + else + for attr in negation[:attributes] + if element.attributes[attr[0]] =~ attr[1] + matched = false + break + end + end + end + if matched + for pseudo in negation[:pseudo] + if pseudo.call(element) + matched = false + break + end + end + end + break unless matched + end + end + + # If element matched but depends on another element (child, + # sibling, etc), apply the dependent matches instead. + if matched && @depends + matches = @depends.call(element, first_only) + else + matches = matched ? [element] : nil + end + + # If this selector is part of the group, try all the alternative + # selectors (unless first_only). + if !first_only || !matches + @alternates.each do |alternate| + break if matches && first_only + if subset = alternate.match(element, first_only) + if matches + matches.concat subset + else + matches = subset + end + end + end + end + + matches + end + + + # :call-seq: + # select(root) => array + # + # Selects and returns an array with all matching elements, beginning + # with one node and traversing through all children depth-first. + # Returns an empty array if no match is found. + # + # The root node may be any element in the document, or the document + # itself. + # + # For example: + # selector = HTML::Selector.new "input[type=text]" + # matches = selector.select(element) + # matches.each do |match| + # puts "Found text field with name #{match.attributes['name']}" + # end + def select(root) + matches = [] + stack = [root] + while node = stack.pop + if node.tag? && subset = match(node, false) + subset.each do |match| + matches << match unless matches.any? { |item| item.equal?(match) } + end + elsif children = node.children + stack.concat children.reverse + end + end + matches + end + + + # Similar to #select but returns the first matching element. Returns +nil+ + # if no element matches the selector. + def select_first(root) + stack = [root] + while node = stack.pop + if node.tag? && subset = match(node, true) + return subset.first if !subset.empty? + elsif children = node.children + stack.concat children.reverse + end + end + nil + end + + + def to_s #:nodoc: + @source + end + + + # Return the next element after this one. Skips sibling text nodes. + # + # With the +name+ argument, returns the next element with that name, + # skipping other sibling elements. + def next_element(element, name = nil) + if siblings = element.parent.children + found = false + siblings.each do |node| + if node.equal?(element) + found = true + elsif found && node.tag? + return node if (name.nil? || node.name == name) + end + end + end + nil + end + + + protected + + + # Creates a simple selector given the statement and array of + # substitution values. + # + # Returns a hash with the values +tag_name+, +attributes+, + # +pseudo+ (classes) and +negation+. + # + # Called the first time with +can_negate+ true to allow + # negation. Called a second time with false since negation + # cannot be negated. + def simple_selector(statement, values, can_negate = true) + tag_name = nil + attributes = [] + pseudo = [] + negation = [] + + # Element name. (Note that in negation, this can come at + # any order, but for simplicity we allow if only first). + statement.sub!(/^(\*|[[:alpha:]][\w\-]*)/) do |match| + match.strip! + tag_name = match.downcase unless match == "*" + @source << match + "" # Remove + end + + # Get identifier, class, attribute name, pseudo or negation. + while true + # Element identifier. + next if statement.sub!(/^#(\?|[\w\-]+)/) do + id = $1 + if id == "?" + id = values.shift + end + @source << "##{id}" + id = Regexp.new("^#{Regexp.escape(id.to_s)}$") unless id.is_a?(Regexp) + attributes << ["id", id] + "" # Remove + end + + # Class name. + next if statement.sub!(/^\.([\w\-]+)/) do + class_name = $1 + @source << ".#{class_name}" + class_name = Regexp.new("(^|\s)#{Regexp.escape(class_name)}($|\s)") unless class_name.is_a?(Regexp) + attributes << ["class", class_name] + "" # Remove + end + + # Attribute value. + next if statement.sub!(/^\[\s*([[:alpha:]][\w\-:]*)\s*((?:[~|^$*])?=)?\s*('[^']*'|"[^*]"|[^\]]*)\s*\]/) do + name, equality, value = $1, $2, $3 + if value == "?" + value = values.shift + else + # Handle single and double quotes. + value.strip! + if (value[0] == ?" || value[0] == ?') && value[0] == value[-1] + value = value[1..-2] + end + end + @source << "[#{name}#{equality}'#{value}']" + attributes << [name.downcase.strip, attribute_match(equality, value)] + "" # Remove + end + + # Root element only. + next if statement.sub!(/^:root/) do + pseudo << lambda do |element| + element.parent.nil? || !element.parent.tag? + end + @source << ":root" + "" # Remove + end + + # Nth-child including last and of-type. + next if statement.sub!(/^:nth-(last-)?(child|of-type)\((odd|even|(\d+|\?)|(-?\d*|\?)?n([+\-]\d+|\?)?)\)/) do |match| + reverse = $1 == "last-" + of_type = $2 == "of-type" + @source << ":nth-#{$1}#{$2}(" + case $3 + when "odd" + pseudo << nth_child(2, 1, of_type, reverse) + @source << "odd)" + when "even" + pseudo << nth_child(2, 2, of_type, reverse) + @source << "even)" + when /^(\d+|\?)$/ # b only + b = ($1 == "?" ? values.shift : $1).to_i + pseudo << nth_child(0, b, of_type, reverse) + @source << "#{b})" + when /^(-?\d*|\?)?n([+\-]\d+|\?)?$/ + a = ($1 == "?" ? values.shift : + $1 == "" ? 1 : $1 == "-" ? -1 : $1).to_i + b = ($2 == "?" ? values.shift : $2).to_i + pseudo << nth_child(a, b, of_type, reverse) + @source << (b >= 0 ? "#{a}n+#{b})" : "#{a}n#{b})") + else + raise ArgumentError, "Invalid nth-child #{match}" + end + "" # Remove + end + # First/last child (of type). + next if statement.sub!(/^:(first|last)-(child|of-type)/) do + reverse = $1 == "last" + of_type = $2 == "of-type" + pseudo << nth_child(0, 1, of_type, reverse) + @source << ":#{$1}-#{$2}" + "" # Remove + end + # Only child (of type). + next if statement.sub!(/^:only-(child|of-type)/) do + of_type = $1 == "of-type" + pseudo << only_child(of_type) + @source << ":only-#{$1}" + "" # Remove + end + + # Empty: no child elements or meaningful content (whitespaces + # are ignored). + next if statement.sub!(/^:empty/) do + pseudo << lambda do |element| + empty = true + for child in element.children + if child.tag? || !child.content.strip.empty? + empty = false + break + end + end + empty + end + @source << ":empty" + "" # Remove + end + # Content: match the text content of the element, stripping + # leading and trailing spaces. + next if statement.sub!(/^:content\(\s*(\?|'[^']*'|"[^"]*"|[^)]*)\s*\)/) do + content = $1 + if content == "?" + content = values.shift + elsif (content[0] == ?" || content[0] == ?') && content[0] == content[-1] + content = content[1..-2] + end + @source << ":content('#{content}')" + content = Regexp.new("^#{Regexp.escape(content.to_s)}$") unless content.is_a?(Regexp) + pseudo << lambda do |element| + text = "" + for child in element.children + unless child.tag? + text << child.content + end + end + text.strip =~ content + end + "" # Remove + end + + # Negation. Create another simple selector to handle it. + if statement.sub!(/^:not\(\s*/, "") + raise ArgumentError, "Double negatives are not missing feature" unless can_negate + @source << ":not(" + negation << simple_selector(statement, values, false) + raise ArgumentError, "Negation not closed" unless statement.sub!(/^\s*\)/, "") + @source << ")" + next + end + + # No match: moving on. + break + end + + # Return hash. The keys are mapped to instance variables. + {:tag_name=>tag_name, :attributes=>attributes, :pseudo=>pseudo, :negation=>negation} + end + + + # Create a regular expression to match an attribute value based + # on the equality operator (=, ^=, |=, etc). + def attribute_match(equality, value) + regexp = value.is_a?(Regexp) ? value : Regexp.escape(value.to_s) + case equality + when "=" then + # Match the attribute value in full + Regexp.new("^#{regexp}$") + when "~=" then + # Match a space-separated word within the attribute value + Regexp.new("(^|\s)#{regexp}($|\s)") + when "^=" + # Match the beginning of the attribute value + Regexp.new("^#{regexp}") + when "$=" + # Match the end of the attribute value + Regexp.new("#{regexp}$") + when "*=" + # Match substring of the attribute value + regexp.is_a?(Regexp) ? regexp : Regexp.new(regexp) + when "|=" then + # Match the first space-separated item of the attribute value + Regexp.new("^#{regexp}($|\s)") + else + raise InvalidSelectorError, "Invalid operation/value" unless value.empty? + # Match all attributes values (existence check) + // + end + end + + + # Returns a lambda that can match an element against the nth-child + # pseudo class, given the following arguments: + # * +a+ -- Value of a part. + # * +b+ -- Value of b part. + # * +of_type+ -- True to test only elements of this type (of-type). + # * +reverse+ -- True to count in reverse order (last-). + def nth_child(a, b, of_type, reverse) + # a = 0 means select at index b, if b = 0 nothing selected + return lambda { |element| false } if a == 0 && b == 0 + # a < 0 and b < 0 will never match against an index + return lambda { |element| false } if a < 0 && b < 0 + b = a + b + 1 if b < 0 # b < 0 just picks last element from each group + b -= 1 unless b == 0 # b == 0 is same as b == 1, otherwise zero based + lambda do |element| + # Element must be inside parent element. + return false unless element.parent && element.parent.tag? + index = 0 + # Get siblings, reverse if counting from last. + siblings = element.parent.children + siblings = siblings.reverse if reverse + # Match element name if of-type, otherwise ignore name. + name = of_type ? element.name : nil + found = false + for child in siblings + # Skip text nodes/comments. + if child.tag? && (name == nil || child.name == name) + if a == 0 + # Shortcut when a == 0 no need to go past count + if index == b + found = child.equal?(element) + break + end + elsif a < 0 + # Only look for first b elements + break if index > b + if child.equal?(element) + found = (index % a) == 0 + break + end + else + # Otherwise, break if child found and count == an+b + if child.equal?(element) + found = (index % a) == b + break + end + end + index += 1 + end + end + found + end + end + + + # Creates a only child lambda. Pass +of-type+ to only look at + # elements of its type. + def only_child(of_type) + lambda do |element| + # Element must be inside parent element. + return false unless element.parent && element.parent.tag? + name = of_type ? element.name : nil + other = false + for child in element.parent.children + # Skip text nodes/comments. + if child.tag? && (name == nil || child.name == name) + unless child.equal?(element) + other = true + break + end + end + end + !other + end + end + + + # Called to create a dependent selector (sibling, descendant, etc). + # Passes the remainder of the statement that will be reduced to zero + # eventually, and array of substitution values. + # + # This method is called from four places, so it helps to put it here + # for reuse. The only logic deals with the need to detect comma + # separators (alternate) and apply them to the selector group of the + # top selector. + def next_selector(statement, values) + second = Selector.new(statement, values) + # If there are alternate selectors, we group them in the top selector. + if alternates = second.instance_variable_get(:@alternates) + second.instance_variable_set(:@alternates, []) + @alternates.concat alternates + end + second + end + + end + + + # See HTML::Selector.new + def self.selector(statement, *values) + Selector.new(statement, *values) + end + + + class Tag + + def select(selector, *values) + selector = HTML::Selector.new(selector, values) + selector.select(self) + end + + end + +end diff --git a/actionview/lib/action_view/vendor/html-scanner/html/tokenizer.rb b/actionview/lib/action_view/vendor/html-scanner/html/tokenizer.rb new file mode 100644 index 0000000000..8ac8d34430 --- /dev/null +++ b/actionview/lib/action_view/vendor/html-scanner/html/tokenizer.rb @@ -0,0 +1,107 @@ +require 'strscan' + +module HTML #:nodoc: + + # A simple HTML tokenizer. It simply breaks a stream of text into tokens, where each + # token is a string. Each string represents either "text", or an HTML element. + # + # This currently assumes valid XHTML, which means no free < or > characters. + # + # Usage: + # + # tokenizer = HTML::Tokenizer.new(text) + # while token = tokenizer.next + # p token + # end + class Tokenizer #:nodoc: + + # The current (byte) position in the text + attr_reader :position + + # The current line number + attr_reader :line + + # Create a new Tokenizer for the given text. + def initialize(text) + text.encode! + @scanner = StringScanner.new(text) + @position = 0 + @line = 0 + @current_line = 1 + end + + # Return the next token in the sequence, or +nil+ if there are no more tokens in + # the stream. + def next + return nil if @scanner.eos? + @position = @scanner.pos + @line = @current_line + if @scanner.check(/<\S/) + update_current_line(scan_tag) + else + update_current_line(scan_text) + end + end + + private + + # Treat the text at the current position as a tag, and scan it. Supports + # comments, doctype tags, and regular tags, and ignores less-than and + # greater-than characters within quoted strings. + def scan_tag + tag = @scanner.getch + if @scanner.scan(/!--/) # comment + tag << @scanner.matched + tag << (@scanner.scan_until(/--\s*>/) || @scanner.scan_until(/\Z/)) + elsif @scanner.scan(/!\[CDATA\[/) + tag << @scanner.matched + tag << (@scanner.scan_until(/\]\]>/) || @scanner.scan_until(/\Z/)) + elsif @scanner.scan(/!/) # doctype + tag << @scanner.matched + tag << consume_quoted_regions + else + tag << consume_quoted_regions + end + tag + end + + # Scan all text up to the next < character and return it. + def scan_text + "#{@scanner.getch}#{@scanner.scan(/[^<]*/)}" + end + + # Counts the number of newlines in the text and updates the current line + # accordingly. + def update_current_line(text) + text.scan(/\r?\n/) { @current_line += 1 } + end + + # Skips over quoted strings, so that less-than and greater-than characters + # within the strings are ignored. + def consume_quoted_regions + text = "" + loop do + match = @scanner.scan_until(/['"<>]/) or break + + delim = @scanner.matched + if delim == "<" + match = match.chop + @scanner.pos -= 1 + end + + text << match + break if delim == "<" || delim == ">" + + # consume the quoted region + while match = @scanner.scan_until(/[\\#{delim}]/) + text << match + break if @scanner.matched == delim + break if @scanner.eos? + text << @scanner.getch # skip the escaped character + end + end + text + end + end + +end diff --git a/actionview/lib/action_view/vendor/html-scanner/html/version.rb b/actionview/lib/action_view/vendor/html-scanner/html/version.rb new file mode 100644 index 0000000000..6d645c3e14 --- /dev/null +++ b/actionview/lib/action_view/vendor/html-scanner/html/version.rb @@ -0,0 +1,11 @@ +module HTML #:nodoc: + module Version #:nodoc: + + MAJOR = 0 + MINOR = 5 + TINY = 3 + + STRING = [ MAJOR, MINOR, TINY ].join(".") + + end +end |