REXML Trees
Synced with latest HTML5lib. Added preliminary support (currently disabled) for sanitizing REXML trees.
This commit is contained in:
Jacques Distler
parent
4dd70af5ae
commit
bd8ba1f4b1
28 changed files with 1317 additions and 112 deletions
|
|
@ -148,6 +148,26 @@ module HTML5lib
|
|||
input
|
||||
]
|
||||
|
||||
BOOLEAN_ATTRIBUTES = {
|
||||
:global => %w[irrelevant],
|
||||
'style' => %w[scoped],
|
||||
'img' => %w[ismap],
|
||||
'audio' => %w[autoplay controls],
|
||||
'video' => %w[autoplay controls],
|
||||
'script' => %w[defer async],
|
||||
'details' => %w[open],
|
||||
'datagrid' => %w[multiple disabled],
|
||||
'command' => %w[hidden disabled checked default],
|
||||
'menu' => %w[autosubmit],
|
||||
'fieldset' => %w[disabled readonly],
|
||||
'option' => %w[disabled readonly selected],
|
||||
'optgroup' => %w[disabled readonly],
|
||||
'button' => %w[disabled autofocus],
|
||||
'input' => %w[disabled readonly required autofocus checked ismap],
|
||||
'select' => %w[disabled readonly autofocus multiple],
|
||||
'output' => %w[disabled readonly]
|
||||
}
|
||||
|
||||
# entitiesWindows1252 has to be _ordered_ and needs to have an index.
|
||||
ENTITIES_WINDOWS1252 = [
|
||||
8364, # 0x80 0x20AC EURO SIGN
|
||||
|
|
|
|||
|
|
@ -37,13 +37,13 @@ module HTML5lib
|
|||
# :strict - raise an exception when a parse error is encountered
|
||||
# :tree - a treebuilder class controlling the type of tree that will be
|
||||
# returned. Built in treebuilders can be accessed through
|
||||
# html5lib.treebuilders.getTreeBuilder(treeType)
|
||||
# HTML5lib::TreeBuilders[treeType]
|
||||
def initialize(options = {})
|
||||
@strict = false
|
||||
@errors = []
|
||||
|
||||
@tokenizer = HTMLTokenizer
|
||||
@tree = TreeBuilders::REXMLTree::TreeBuilder
|
||||
@tree = TreeBuilders::REXML::TreeBuilder
|
||||
|
||||
options.each { |name, value| instance_variable_set("@#{name}", value) }
|
||||
|
||||
|
|
|
|||
|
|
@ -107,4 +107,4 @@ module HTML5lib
|
|||
end
|
||||
|
||||
end
|
||||
end
|
||||
end
|
||||
|
|
|
|||
|
|
@ -153,4 +153,4 @@ module HTML5lib
|
|||
end
|
||||
|
||||
end
|
||||
end
|
||||
end
|
||||
|
|
|
|||
|
|
@ -58,7 +58,7 @@ module HTML5lib
|
|||
unless @char_encoding == 'utf-8'
|
||||
begin
|
||||
require 'iconv'
|
||||
uString = Iconv.iconv('utf-8', @encoding, uString)[0]
|
||||
uString = Iconv.iconv('utf-8', @char_encoding, uString)[0]
|
||||
rescue
|
||||
end
|
||||
end
|
||||
|
|
@ -95,11 +95,13 @@ module HTML5lib
|
|||
#First look for a BOM
|
||||
#This will also read past the BOM if present
|
||||
encoding = detect_bom
|
||||
|
||||
#If there is no BOM need to look for meta elements with encoding
|
||||
#information
|
||||
if encoding.nil? and @parse_meta
|
||||
encoding = detect_encoding_meta
|
||||
end
|
||||
|
||||
#Guess with chardet, if avaliable
|
||||
if encoding.nil? and @chardet
|
||||
begin
|
||||
|
|
@ -111,13 +113,14 @@ module HTML5lib
|
|||
rescue LoadError
|
||||
end
|
||||
end
|
||||
|
||||
# If all else fails use the default encoding
|
||||
if encoding.nil?
|
||||
encoding = @DEFAULT_ENCODING
|
||||
end
|
||||
|
||||
#Substitute for equivalent encodings:
|
||||
encoding_sub = {'ascii' => 'windows-1252', 'iso-8859-1' => 'windows-1252'}
|
||||
encoding_sub = {'iso-8859-1' => 'windows-1252'}
|
||||
|
||||
if encoding_sub.has_key?(encoding.downcase)
|
||||
encoding = encoding_sub[encoding.downcase]
|
||||
|
|
@ -132,10 +135,10 @@ module HTML5lib
|
|||
def detect_bom
|
||||
bom_dict = {
|
||||
"\xef\xbb\xbf" => 'utf-8',
|
||||
"\xff\xfe" => 'utf-16-le',
|
||||
"\xfe\xff" => 'utf-16-be',
|
||||
"\xff\xfe\x00\x00" => 'utf-32-le',
|
||||
"\x00\x00\xfe\xff" => 'utf-32-be'
|
||||
"\xff\xfe" => 'utf16le',
|
||||
"\xfe\xff" => 'utf16be',
|
||||
"\xff\xfe\x00\x00" => 'utf32le',
|
||||
"\x00\x00\xfe\xff" => 'utf32be'
|
||||
}
|
||||
|
||||
# Go to beginning of file and read in 4 bytes
|
||||
|
|
@ -205,7 +208,17 @@ module HTML5lib
|
|||
else
|
||||
begin
|
||||
@tell += 1
|
||||
return @data_stream[@tell - 1].chr
|
||||
c = @data_stream[@tell - 1]
|
||||
case c
|
||||
when 0xC2 .. 0xDF
|
||||
@tell += 1
|
||||
c.chr + @data_stream[@tell-1].chr
|
||||
when 0xE0 .. 0xF0
|
||||
@tell += 2
|
||||
c.chr + @data_stream[@tell-2].chr + @data_stream[@tell-1].chr
|
||||
else
|
||||
c.chr
|
||||
end
|
||||
rescue
|
||||
return :EOF
|
||||
end
|
||||
|
|
@ -227,8 +240,8 @@ module HTML5lib
|
|||
else
|
||||
# Then the rest
|
||||
begin
|
||||
char_stack.push(@data_stream[@tell].chr)
|
||||
@tell += 1
|
||||
char_stack.push(@data_stream[@tell-1].chr)
|
||||
rescue
|
||||
char_stack.push(:EOF)
|
||||
break
|
||||
|
|
|
|||
|
|
@ -1,4 +1,3 @@
|
|||
require 'html5lib/tokenizer'
|
||||
require 'cgi'
|
||||
|
||||
module HTML5lib
|
||||
|
|
@ -6,7 +5,7 @@ module HTML5lib
|
|||
# This module provides sanitization of XHTML+MathML+SVG
|
||||
# and of inline style attributes.
|
||||
|
||||
class HTMLSanitizer < HTMLTokenizer
|
||||
module HTMLSanitizeModule
|
||||
|
||||
ACCEPTABLE_ELEMENTS = %w[a abbr acronym address area b big blockquote br
|
||||
button caption center cite code col colgroup dd del dfn dir div dl dt
|
||||
|
|
@ -96,19 +95,7 @@ module HTML5lib
|
|||
ALLOWED_SVG_PROPERTIES = ACCEPTABLE_SVG_PROPERTIES
|
||||
ALLOWED_PROTOCOLS = ACCEPTABLE_PROTOCOLS
|
||||
|
||||
# Sanitize the +html+, escaping all elements not in ALLOWED_ELEMENTS, and
|
||||
# stripping out all # attributes not in ALLOWED_ATTRIBUTES. Style
|
||||
# attributes are parsed, and a restricted set, # specified by
|
||||
# ALLOWED_CSS_PROPERTIES and ALLOWED_CSS_KEYWORDS, are allowed through.
|
||||
# attributes in ATTR_VAL_IS_URI are scanned, and only URI schemes specified
|
||||
# in ALLOWED_PROTOCOLS are allowed.
|
||||
#
|
||||
# sanitize_html('<script> do_nasty_stuff() </script>')
|
||||
# => <script> do_nasty_stuff() </script>
|
||||
# sanitize_html('<a href="javascript: sucker();">Click here for $100</a>')
|
||||
# => <a>Click here for $100</a>
|
||||
def each
|
||||
super do |token|
|
||||
def process_token(token)
|
||||
case token[:type]
|
||||
when :StartTag, :EndTag, :EmptyTag
|
||||
if ALLOWED_ELEMENTS.include?(token[:name])
|
||||
|
|
@ -126,7 +113,7 @@ module HTML5lib
|
|||
end
|
||||
token[:data] = attrs.map {|k,v| [k,v]}
|
||||
end
|
||||
yield token
|
||||
return token
|
||||
else
|
||||
if token[:type] == :EndTag
|
||||
token[:data] = "</#{token[:name]}>"
|
||||
|
|
@ -139,12 +126,11 @@ module HTML5lib
|
|||
token[:data].insert(-2,'/') if token[:type] == :EmptyTag
|
||||
token[:type] = :Characters
|
||||
token.delete(:name)
|
||||
yield token
|
||||
return token
|
||||
end
|
||||
else
|
||||
yield token
|
||||
return token
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
def sanitize_css(style)
|
||||
|
|
@ -174,4 +160,23 @@ module HTML5lib
|
|||
style = clean.join(' ')
|
||||
end
|
||||
end
|
||||
|
||||
class HTMLSanitizeFilter < Filter
|
||||
include HTMLSanitizeModule
|
||||
def each
|
||||
@source.each do |token|
|
||||
yield(process_token(token))
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
class HTMLSanitizer < HTMLTokenizer
|
||||
include HTMLSanitizeModule
|
||||
def each
|
||||
super do |token|
|
||||
yield(process_token(token))
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
end
|
||||
|
|
|
|||
418
vendor/plugins/HTML5lib/lib/html5lib/serializer.rb
vendored
Normal file
418
vendor/plugins/HTML5lib/lib/html5lib/serializer.rb
vendored
Normal file
|
|
@ -0,0 +1,418 @@
|
|||
require 'html5lib/constants'
|
||||
require 'jcode'
|
||||
|
||||
module HTML5lib
|
||||
|
||||
class Filter
|
||||
include Enumerable
|
||||
def initialize(source)
|
||||
@source = source
|
||||
end
|
||||
end
|
||||
|
||||
class OptionalTagFilter < Filter
|
||||
def slider
|
||||
previous1 = previous2 = nil
|
||||
@source.each do |token|
|
||||
yield previous2, previous1, token if previous1 != nil
|
||||
previous2 = previous1
|
||||
previous1 = token
|
||||
end
|
||||
yield previous2, previous1, nil
|
||||
end
|
||||
|
||||
def each
|
||||
slider do |previous, token, nexttok|
|
||||
type = token[:type]
|
||||
if type == :StartTag
|
||||
yield token unless token[:data].empty? and is_optional_start(token[:name], previous, nexttok)
|
||||
elsif type == :EndTag
|
||||
yield token unless is_optional_end(token[:name], nexttok)
|
||||
else
|
||||
yield token
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
def is_optional_start(tagname, previous, nexttok)
|
||||
type = nexttok ? nexttok[:type] : nil
|
||||
if tagname == 'html'
|
||||
# An html element's start tag may be omitted if the first thing
|
||||
# inside the html element is not a space character or a comment.
|
||||
return ![:Comment, :SpaceCharacters].include?(type)
|
||||
elsif tagname == 'head'
|
||||
# A head element's start tag may be omitted if the first thing
|
||||
# inside the head element is an element.
|
||||
return type == :StartTag
|
||||
elsif tagname == 'body'
|
||||
# A body element's start tag may be omitted if the first thing
|
||||
# inside the body element is not a space character or a comment,
|
||||
# except if the first thing inside the body element is a script
|
||||
# or style element and the node immediately preceding the body
|
||||
# element is a head element whose end tag has been omitted.
|
||||
if [:Comment, :SpaceCharacters].include?(type)
|
||||
return false
|
||||
elsif type == :StartTag
|
||||
# XXX: we do not look at the preceding event, so we never omit
|
||||
# the body element's start tag if it's followed by a script or
|
||||
# a style element.
|
||||
return !%w[script style].include?(nexttok[:name])
|
||||
else
|
||||
return true
|
||||
end
|
||||
elsif tagname == 'colgroup'
|
||||
# A colgroup element's start tag may be omitted if the first thing
|
||||
# inside the colgroup element is a col element, and if the element
|
||||
# is not immediately preceeded by another colgroup element whose
|
||||
# end tag has been omitted.
|
||||
if type == :StartTag
|
||||
# XXX: we do not look at the preceding event, so instead we never
|
||||
# omit the colgroup element's end tag when it is immediately
|
||||
# followed by another colgroup element. See is_optional_end.
|
||||
return nexttok[:name] == "col"
|
||||
else
|
||||
return false
|
||||
end
|
||||
elsif tagname == 'tbody'
|
||||
# A tbody element's start tag may be omitted if the first thing
|
||||
# inside the tbody element is a tr element, and if the element is
|
||||
# not immediately preceeded by a tbody, thead, or tfoot element
|
||||
# whose end tag has been omitted.
|
||||
if type == :StartTag
|
||||
# omit the thead and tfoot elements' end tag when they are
|
||||
# immediately followed by a tbody element. See is_optional_end.
|
||||
if previous and previous[:type] == :EndTag and \
|
||||
%w(tbody thead tfoot).include?(previous[:name])
|
||||
return false
|
||||
end
|
||||
|
||||
return nexttok[:name] == 'tr'
|
||||
else
|
||||
return false
|
||||
end
|
||||
end
|
||||
return false
|
||||
end
|
||||
|
||||
def is_optional_end(tagname, nexttok)
|
||||
type = nexttok ? nexttok[:type] : nil
|
||||
if %w[html head body].include?(tagname)
|
||||
# An html element's end tag may be omitted if the html element
|
||||
# is not immediately followed by a space character or a comment.
|
||||
return ![:Comment, :SpaceCharacters].include?(type)
|
||||
elsif %w[li optgroup option tr].include?(tagname)
|
||||
# A li element's end tag may be omitted if the li element is
|
||||
# immediately followed by another li element or if there is
|
||||
# no more content in the parent element.
|
||||
# An optgroup element's end tag may be omitted if the optgroup
|
||||
# element is immediately followed by another optgroup element,
|
||||
# or if there is no more content in the parent element.
|
||||
# An option element's end tag may be omitted if the option
|
||||
# element is immediately followed by another option element,
|
||||
# or if there is no more content in the parent element.
|
||||
# A tr element's end tag may be omitted if the tr element is
|
||||
# immediately followed by another tr element, or if there is
|
||||
# no more content in the parent element.
|
||||
if type == :StartTag
|
||||
return nexttok[:name] == tagname
|
||||
else
|
||||
return type == :EndTag || type == nil
|
||||
end
|
||||
elsif %w(dt dd).include?(tagname)
|
||||
# A dt element's end tag may be omitted if the dt element is
|
||||
# immediately followed by another dt element or a dd element.
|
||||
# A dd element's end tag may be omitted if the dd element is
|
||||
# immediately followed by another dd element or a dt element,
|
||||
# or if there is no more content in the parent element.
|
||||
if type == :StartTag
|
||||
return %w(dt dd).include?(nexttok[:name])
|
||||
elsif tagname == 'dd'
|
||||
return type == :EndTag || type == nil
|
||||
else
|
||||
return false
|
||||
end
|
||||
elsif tagname == 'p'
|
||||
# A p element's end tag may be omitted if the p element is
|
||||
# immediately followed by an address, blockquote, dl, fieldset,
|
||||
# form, h1, h2, h3, h4, h5, h6, hr, menu, ol, p, pre, table,
|
||||
# or ul element, or if there is no more content in the parent
|
||||
# element.
|
||||
if type == :StartTag
|
||||
return %w(address blockquote dl fieldset form h1 h2 h3 h4 h5
|
||||
h6 hr menu ol p pre table ul).include?(nexttok[:name])
|
||||
else
|
||||
return type == :EndTag || type == nil
|
||||
end
|
||||
elsif tagname == 'colgroup'
|
||||
# A colgroup element's end tag may be omitted if the colgroup
|
||||
# element is not immediately followed by a space character or
|
||||
# a comment.
|
||||
if [:Comment, :SpaceCharacters].include?(type)
|
||||
return false
|
||||
elsif type == :StartTag
|
||||
# XXX: we also look for an immediately following colgroup
|
||||
# element. See is_optional_start.
|
||||
return nexttok[:name] != 'colgroup'
|
||||
else
|
||||
return true
|
||||
end
|
||||
elsif %w(thead tbody).include? tagname
|
||||
# A thead element's end tag may be omitted if the thead element
|
||||
# is immediately followed by a tbody or tfoot element.
|
||||
# A tbody element's end tag may be omitted if the tbody element
|
||||
# is immediately followed by a tbody or tfoot element, or if
|
||||
# there is no more content in the parent element.
|
||||
# A tfoot element's end tag may be omitted if the tfoot element
|
||||
# is immediately followed by a tbody element, or if there is no
|
||||
# more content in the parent element.
|
||||
# XXX: we never omit the end tag when the following element is
|
||||
# a tbody. See is_optional_start.
|
||||
if type == :StartTag
|
||||
return %w(tbody tfoot).include?(nexttok[:name])
|
||||
elsif tagname == 'tbody'
|
||||
return (type == :EndTag or type == nil)
|
||||
else
|
||||
return false
|
||||
end
|
||||
elsif tagname == 'tfoot'
|
||||
# A tfoot element's end tag may be omitted if the tfoot element
|
||||
# is immediately followed by a tbody element, or if there is no
|
||||
# more content in the parent element.
|
||||
# XXX: we never omit the end tag when the following element is
|
||||
# a tbody. See is_optional_start.
|
||||
if type == :StartTag
|
||||
return nexttok[:name] == 'tbody'
|
||||
else
|
||||
return type == :EndTag || type == nil
|
||||
end
|
||||
elsif %w(td th).include? tagname
|
||||
# A td element's end tag may be omitted if the td element is
|
||||
# immediately followed by a td or th element, or if there is
|
||||
# no more content in the parent element.
|
||||
# A th element's end tag may be omitted if the th element is
|
||||
# immediately followed by a td or th element, or if there is
|
||||
# no more content in the parent element.
|
||||
if type == :StartTag
|
||||
return %w(td th).include?(nexttok[:name])
|
||||
else
|
||||
return type == :EndTag || type == nil
|
||||
end
|
||||
end
|
||||
return false
|
||||
end
|
||||
end
|
||||
|
||||
class HTMLSerializer
|
||||
CDATA_ELEMENTS = %w[style script xmp iframe noembed noframes noscript]
|
||||
|
||||
def self.serialize(stream, options = {})
|
||||
new(options).serialize(stream)
|
||||
end
|
||||
|
||||
def initialize(options={})
|
||||
@quote_attr_values = false
|
||||
@quote_char = '"'
|
||||
@use_best_quote_char = true
|
||||
@minimize_boolean_attributes = true
|
||||
|
||||
@use_trailing_solidus = false
|
||||
@space_before_trailing_solidus = true
|
||||
|
||||
@omit_optional_tags = true
|
||||
@sanitize = false
|
||||
|
||||
@strip_whitespace = false
|
||||
|
||||
@inject_meta_charset = true
|
||||
|
||||
options.each do |name, value|
|
||||
next unless %w(quote_attr_values quote_char use_best_quote_char
|
||||
minimize_boolean_attributes use_trailing_solidus
|
||||
space_before_trailing_solidus omit_optional_tags sanitize
|
||||
strip_whitespace inject_meta_charset).include? name.to_s
|
||||
@use_best_quote_char = false if name.to_s == 'quote_char'
|
||||
instance_variable_set("@#{name}", value)
|
||||
end
|
||||
|
||||
@errors = []
|
||||
end
|
||||
|
||||
def serialize(treewalker, encoding=nil)
|
||||
in_cdata = false
|
||||
@errors = []
|
||||
if encoding and @inject_meta_charset
|
||||
treewalker = filter_inject_meta_charset(treewalker, encoding)
|
||||
end
|
||||
if @strip_whitespace
|
||||
treewalker = filter_whitespace(treewalker)
|
||||
end
|
||||
if @sanitize
|
||||
require 'html5lib/sanitizer'
|
||||
treewalker = HTMLSanitizeFilter.new(treewalker)
|
||||
end
|
||||
# if @omit_optional_tags
|
||||
# treewalker = OptionalTagFilter.new(treewalker)
|
||||
# end
|
||||
|
||||
result = []
|
||||
treewalker.each do |token|
|
||||
type = token[:type]
|
||||
if type == :Doctype
|
||||
doctype = "<!DOCTYPE %s>" % token[:name]
|
||||
if encoding
|
||||
result << doctype.encode(encoding)
|
||||
else
|
||||
result << doctype
|
||||
end
|
||||
|
||||
elsif [:Characters, :SpaceCharacters].include? type
|
||||
if type == :SpaceCharacters or in_cdata
|
||||
if in_cdata and token[:data].find("</") >= 0
|
||||
serializeError(_("Unexpected </ in CDATA"))
|
||||
end
|
||||
if encoding
|
||||
result << token[:data].encode(encoding, errors || "strict")
|
||||
else
|
||||
result << token[:data]
|
||||
end
|
||||
elsif encoding
|
||||
result << token[:data].replace("&", "&") \
|
||||
.encode(encoding, unicode_encode_errors)
|
||||
else
|
||||
result << token[:data] \
|
||||
.gsub("&", "&") \
|
||||
.gsub("<", "<") \
|
||||
.gsub(">", ">")
|
||||
end
|
||||
|
||||
elsif [:StartTag, :EmptyTag].include? type
|
||||
name = token[:name]
|
||||
if CDATA_ELEMENTS.include?(name)
|
||||
in_cdata = true
|
||||
elsif in_cdata
|
||||
serializeError(_("Unexpected child element of a CDATA element"))
|
||||
end
|
||||
attrs = token[:data].to_a
|
||||
attrs.sort()
|
||||
attributes = []
|
||||
for k,v in attrs
|
||||
if encoding
|
||||
k = k.encode(encoding)
|
||||
end
|
||||
attributes << ' '
|
||||
|
||||
attributes << k
|
||||
if not @minimize_boolean_attributes or \
|
||||
(!(BOOLEAN_ATTRIBUTES[name]||[]).include?(k) \
|
||||
and !BOOLEAN_ATTRIBUTES[:global].include?(k))
|
||||
attributes << "="
|
||||
if @quote_attr_values or v.empty?
|
||||
quote_attr = true
|
||||
else
|
||||
quote_attr = (SPACE_CHARACTERS.join('') + "<>\"'").each_char.any? {|c| v.include?(c)}
|
||||
end
|
||||
v = v.gsub("&", "&")
|
||||
if encoding
|
||||
v = v.encode(encoding, unicode_encode_errors)
|
||||
end
|
||||
if quote_attr
|
||||
quote_char = @quote_char
|
||||
if @use_best_quote_char
|
||||
if v.index("'") and !v.index('"')
|
||||
quote_char = '"'
|
||||
elsif v.index('"') and !v.index("'")
|
||||
quote_char = "'"
|
||||
end
|
||||
end
|
||||
if quote_char == "'"
|
||||
v = v.gsub("'", "'")
|
||||
else
|
||||
v = v.gsub('"', """)
|
||||
end
|
||||
attributes << quote_char << v << quote_char
|
||||
else
|
||||
attributes << v
|
||||
end
|
||||
end
|
||||
end
|
||||
if VOID_ELEMENTS.include?(name) and @use_trailing_solidus
|
||||
if @space_before_trailing_solidus
|
||||
attributes << " /"
|
||||
else
|
||||
attributes << "/"
|
||||
end
|
||||
end
|
||||
if encoding
|
||||
result << "<%s%s>" % [name.encode(encoding), attributes.join('')]
|
||||
else
|
||||
result << "<%s%s>" % [name, attributes.join('')]
|
||||
end
|
||||
|
||||
elsif type == :EndTag
|
||||
name = token[:name]
|
||||
if CDATA_ELEMENTS.include?(name)
|
||||
in_cdata = false
|
||||
elsif in_cdata
|
||||
serializeError(_("Unexpected child element of a CDATA element"))
|
||||
end
|
||||
end_tag = "</%s>" % name
|
||||
if encoding
|
||||
end_tag = end_tag.encode(encoding)
|
||||
end
|
||||
result << end_tag
|
||||
|
||||
elsif type == :Comment
|
||||
data = token[:data]
|
||||
if data.index("--")
|
||||
serializeError(_("Comment contains --"))
|
||||
end
|
||||
comment = "<!--%s-->" % token[:data]
|
||||
if encoding
|
||||
comment = comment.encode(encoding, unicode_encode_errors)
|
||||
end
|
||||
result << comment
|
||||
|
||||
else
|
||||
serializeError(token[:data])
|
||||
end
|
||||
end
|
||||
result.join('')
|
||||
end
|
||||
|
||||
def render(treewalker, encoding=nil)
|
||||
if encoding
|
||||
return "".join(list(serialize(treewalker, encoding)))
|
||||
else
|
||||
return "".join(list(serialize(treewalker)))
|
||||
end
|
||||
end
|
||||
|
||||
def serializeError(data="XXX ERROR MESSAGE NEEDED")
|
||||
# XXX The idea is to make data mandatory.
|
||||
@errors.push(data)
|
||||
if @strict
|
||||
raise SerializeError
|
||||
end
|
||||
end
|
||||
|
||||
def filter_inject_meta_charset(treewalker, encoding)
|
||||
done = false
|
||||
for token in treewalker
|
||||
if not done and token[:type] == :StartTag \
|
||||
and token[:name].lower() == "head"
|
||||
yield({:type => :EmptyTag, :name => "meta", \
|
||||
:data => {"charset" => encoding}})
|
||||
end
|
||||
yield token
|
||||
end
|
||||
end
|
||||
|
||||
def filter_whitespace(treewalker)
|
||||
raise NotImplementedError
|
||||
end
|
||||
end
|
||||
|
||||
# Error in serialized tree
|
||||
class SerializeError < Exception
|
||||
end
|
||||
end
|
||||
|
|
@ -1,21 +1,24 @@
|
|||
module HTML5lib
|
||||
module TreeBuilders
|
||||
|
||||
def self.getTreeBuilder(name)
|
||||
case name.to_s.downcase
|
||||
class << self
|
||||
def [](name)
|
||||
case name.to_s.downcase
|
||||
when 'simpletree' then
|
||||
require 'html5lib/treebuilders/simpletree'
|
||||
SimpleTree::TreeBuilder
|
||||
when 'rexml' then
|
||||
require 'html5lib/treebuilders/rexml'
|
||||
REXMLTree::TreeBuilder
|
||||
REXML::TreeBuilder
|
||||
when 'hpricot' then
|
||||
require 'html5lib/treebuilders/hpricot'
|
||||
Hpricot::TreeBuilder
|
||||
else
|
||||
raise "Unknown TreeBuilder #{name}"
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
alias :getTreeBuilder :[]
|
||||
end
|
||||
end
|
||||
end
|
||||
|
|
|
|||
|
|
@ -144,7 +144,7 @@ module HTML5lib
|
|||
# code. It should still do the same though.
|
||||
|
||||
# Step 1: stop the algorithm when there's nothing to do.
|
||||
return unless @activeFormattingElements
|
||||
return if @activeFormattingElements.empty?
|
||||
|
||||
# Step 2 and step 3: we start with the last element. So i is -1.
|
||||
i = -1
|
||||
|
|
|
|||
|
|
@ -1,4 +1,5 @@
|
|||
require 'html5lib/treebuilders/base'
|
||||
require 'rubygems'
|
||||
require 'hpricot'
|
||||
require 'forwardable'
|
||||
|
||||
|
|
@ -26,12 +27,14 @@ module HTML5lib
|
|||
childNodes << node
|
||||
hpricot.children << node.hpricot
|
||||
end
|
||||
node.hpricot.parent = hpricot
|
||||
node.parent = self
|
||||
end
|
||||
|
||||
def removeChild(node)
|
||||
childNodes.delete(node)
|
||||
hpricot.children.delete_at(hpricot.children.index(node.hpricot))
|
||||
node.hpricot.parent = nil
|
||||
node.parent = nil
|
||||
end
|
||||
|
||||
|
|
@ -48,6 +51,7 @@ module HTML5lib
|
|||
if node.kind_of?(TextNode) and index > 0 and childNodes[index-1].kind_of?(TextNode)
|
||||
childNodes[index-1].hpricot.content = childNodes[index-1].hpricot.to_s + node.hpricot.to_s
|
||||
else
|
||||
refNode.hpricot.parent.insert_before(node.hpricot,refNode.hpricot)
|
||||
childNodes.insert(index, node)
|
||||
end
|
||||
end
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@ require 'forwardable'
|
|||
|
||||
module HTML5lib
|
||||
module TreeBuilders
|
||||
module REXMLTree
|
||||
module REXML
|
||||
|
||||
class Node < Base::Node
|
||||
extend Forwardable
|
||||
|
|
@ -52,6 +52,7 @@ module HTML5lib
|
|||
childNodes[index-1].rxobj.raw = true
|
||||
else
|
||||
childNodes.insert index, node
|
||||
refNode.rxobj.parent.insert_before(refNode.rxobj,node.rxobj)
|
||||
end
|
||||
end
|
||||
|
||||
|
|
@ -62,7 +63,7 @@ module HTML5lib
|
|||
|
||||
class Element < Node
|
||||
def self.rxclass
|
||||
REXML::Element
|
||||
::REXML::Element
|
||||
end
|
||||
|
||||
def initialize name
|
||||
|
|
@ -95,7 +96,7 @@ module HTML5lib
|
|||
|
||||
class Document < Node
|
||||
def self.rxclass
|
||||
REXML::Document
|
||||
::REXML::Document
|
||||
end
|
||||
|
||||
def initialize
|
||||
|
|
@ -120,7 +121,7 @@ module HTML5lib
|
|||
|
||||
class DocumentType < Node
|
||||
def self.rxclass
|
||||
REXML::DocType
|
||||
::REXML::DocType
|
||||
end
|
||||
|
||||
def printTree indent=0
|
||||
|
|
@ -145,7 +146,7 @@ module HTML5lib
|
|||
class TextNode < Node
|
||||
def initialize data
|
||||
raw=data.gsub('&','&').gsub('<','<').gsub('>','>')
|
||||
@rxobj = REXML::Text.new(raw, true, nil, true)
|
||||
@rxobj = ::REXML::Text.new(raw, true, nil, true)
|
||||
end
|
||||
|
||||
def printTree indent=0
|
||||
|
|
@ -155,7 +156,7 @@ module HTML5lib
|
|||
|
||||
class CommentNode < Node
|
||||
def self.rxclass
|
||||
REXML::Comment
|
||||
::REXML::Comment
|
||||
end
|
||||
|
||||
def printTree indent=0
|
||||
|
|
|
|||
26
vendor/plugins/HTML5lib/lib/html5lib/treewalkers.rb
vendored
Normal file
26
vendor/plugins/HTML5lib/lib/html5lib/treewalkers.rb
vendored
Normal file
|
|
@ -0,0 +1,26 @@
|
|||
require 'html5lib/treewalkers/base'
|
||||
|
||||
module HTML5lib
|
||||
module TreeWalkers
|
||||
|
||||
class << self
|
||||
def [](name)
|
||||
case name.to_s.downcase
|
||||
when 'simpletree' then
|
||||
require 'html5lib/treewalkers/simpletree'
|
||||
SimpleTree::TreeWalker
|
||||
when 'rexml' then
|
||||
require 'html5lib/treewalkers/rexml'
|
||||
REXML::TreeWalker
|
||||
when 'hpricot' then
|
||||
require 'html5lib/treewalkers/hpricot'
|
||||
Hpricot::TreeWalker
|
||||
else
|
||||
raise "Unknown TreeWalker #{name}"
|
||||
end
|
||||
end
|
||||
|
||||
alias :getTreeWalker :[]
|
||||
end
|
||||
end
|
||||
end
|
||||
156
vendor/plugins/HTML5lib/lib/html5lib/treewalkers/base.rb
vendored
Normal file
156
vendor/plugins/HTML5lib/lib/html5lib/treewalkers/base.rb
vendored
Normal file
|
|
@ -0,0 +1,156 @@
|
|||
require 'html5lib/constants'
|
||||
module HTML5lib
|
||||
module TreeWalkers
|
||||
|
||||
module TokenConstructor
|
||||
def error(msg)
|
||||
return {:type => "SerializeError", :data => msg}
|
||||
end
|
||||
|
||||
def normalizeAttrs(attrs)
|
||||
attrs.to_a
|
||||
end
|
||||
|
||||
def emptyTag(name, attrs, hasChildren=false)
|
||||
error(_("Void element has children")) if hasChildren
|
||||
return({:type => :EmptyTag, :name => name, \
|
||||
:data => normalizeAttrs(attrs)})
|
||||
end
|
||||
|
||||
def startTag(name, attrs)
|
||||
return {:type => :StartTag, :name => name, \
|
||||
:data => normalizeAttrs(attrs)}
|
||||
end
|
||||
|
||||
def endTag(name)
|
||||
return {:type => :EndTag, :name => name, :data => []}
|
||||
end
|
||||
|
||||
def text(data)
|
||||
if data =~ /^([#{SPACE_CHARACTERS.join('')}]+)/
|
||||
yield({:type => :SpaceCharacters, :data => $1})
|
||||
data = data[$1.length .. -1]
|
||||
return if data.empty?
|
||||
end
|
||||
|
||||
if data =~ /([#{SPACE_CHARACTERS.join('')}]+)$/
|
||||
yield({:type => :Characters, :data => data[0 ... -$1.length]})
|
||||
yield({:type => :SpaceCharacters, :data => $1})
|
||||
else
|
||||
yield({:type => :Characters, :data => data})
|
||||
end
|
||||
end
|
||||
|
||||
def comment(data)
|
||||
return {:type => :Comment, :data => data}
|
||||
end
|
||||
|
||||
def doctype(name)
|
||||
return {:type => :Doctype, :name => name, :data => name.upcase() == "HTML"}
|
||||
end
|
||||
|
||||
def unknown(nodeType)
|
||||
return error(_("Unknown node type: ") + nodeType.to_s)
|
||||
end
|
||||
|
||||
def _(str)
|
||||
str
|
||||
end
|
||||
end
|
||||
|
||||
class Base
|
||||
include TokenConstructor
|
||||
|
||||
def initialize(tree)
|
||||
@tree = tree
|
||||
end
|
||||
|
||||
def each
|
||||
raise NotImplementedError
|
||||
end
|
||||
|
||||
alias walk each
|
||||
end
|
||||
|
||||
class NonRecursiveTreeWalker < TreeWalkers::Base
|
||||
def node_details(node)
|
||||
raise NotImplementedError
|
||||
end
|
||||
|
||||
def first_child(node)
|
||||
raise NotImplementedError
|
||||
end
|
||||
|
||||
def next_sibling(node)
|
||||
raise NotImplementedError
|
||||
end
|
||||
|
||||
def parent(node)
|
||||
raise NotImplementedError
|
||||
end
|
||||
|
||||
def each
|
||||
currentNode = @tree
|
||||
while currentNode != nil
|
||||
details = node_details(currentNode)
|
||||
hasChildren = false
|
||||
|
||||
case details.shift
|
||||
when :DOCTYPE
|
||||
yield doctype(*details)
|
||||
|
||||
when :TEXT
|
||||
text(*details) {|token| yield token}
|
||||
|
||||
when :ELEMENT
|
||||
name, attributes, hasChildren = details
|
||||
if VOID_ELEMENTS.include?(name)
|
||||
yield emptyTag(name, attributes.to_a, hasChildren)
|
||||
hasChildren = false
|
||||
else
|
||||
yield startTag(name, attributes.to_a)
|
||||
end
|
||||
|
||||
when :COMMENT
|
||||
yield comment(details[0])
|
||||
|
||||
when :DOCUMENT, :DOCUMENT_FRAGMENT
|
||||
hasChildren = true
|
||||
|
||||
when nil
|
||||
# ignore (REXML::XMLDecl is an example)
|
||||
|
||||
else
|
||||
yield unknown(details[0])
|
||||
end
|
||||
|
||||
firstChild = hasChildren ? first_child(currentNode) : nil
|
||||
if firstChild != nil
|
||||
currentNode = firstChild
|
||||
else
|
||||
while currentNode != nil
|
||||
details = node_details(currentNode)
|
||||
if details.shift == :ELEMENT
|
||||
name, attributes, hasChildren = details
|
||||
yield endTag(name) if !VOID_ELEMENTS.include?(name)
|
||||
end
|
||||
|
||||
if @tree == currentNode
|
||||
currentNode = nil
|
||||
else
|
||||
nextSibling = next_sibling(currentNode)
|
||||
if nextSibling != nil
|
||||
currentNode = nextSibling
|
||||
break
|
||||
end
|
||||
|
||||
currentNode = parent(currentNode)
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
|
||||
end
|
||||
end
|
||||
48
vendor/plugins/HTML5lib/lib/html5lib/treewalkers/hpricot.rb
vendored
Normal file
48
vendor/plugins/HTML5lib/lib/html5lib/treewalkers/hpricot.rb
vendored
Normal file
|
|
@ -0,0 +1,48 @@
|
|||
require 'html5lib/treewalkers/base'
|
||||
require 'rexml/document'
|
||||
|
||||
module HTML5lib
|
||||
module TreeWalkers
|
||||
module Hpricot
|
||||
class TreeWalker < HTML5lib::TreeWalkers::NonRecursiveTreeWalker
|
||||
|
||||
def node_details(node)
|
||||
case node
|
||||
when ::Hpricot::Elem
|
||||
if !node.name
|
||||
[:DOCUMENT_FRAGMENT]
|
||||
else
|
||||
[:ELEMENT, node.name,
|
||||
node.attributes.map {|name,value| [name,value]},
|
||||
!node.empty?]
|
||||
end
|
||||
when ::Hpricot::Text
|
||||
[:TEXT, node.to_plain_text]
|
||||
when ::Hpricot::Comment
|
||||
[:COMMENT, node.content]
|
||||
when ::Hpricot::Doc
|
||||
[:DOCUMENT]
|
||||
when ::Hpricot::DocType
|
||||
[:DOCTYPE, node.target]
|
||||
when ::Hpricot::XMLDecl
|
||||
[nil]
|
||||
else
|
||||
[:UNKNOWN, node.class.inspect]
|
||||
end
|
||||
end
|
||||
|
||||
def first_child(node)
|
||||
node.children.first
|
||||
end
|
||||
|
||||
def next_sibling(node)
|
||||
node.next_node
|
||||
end
|
||||
|
||||
def parent(node)
|
||||
node.parent
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
48
vendor/plugins/HTML5lib/lib/html5lib/treewalkers/rexml.rb
vendored
Normal file
48
vendor/plugins/HTML5lib/lib/html5lib/treewalkers/rexml.rb
vendored
Normal file
|
|
@ -0,0 +1,48 @@
|
|||
require 'html5lib/treewalkers/base'
|
||||
require 'rexml/document'
|
||||
|
||||
module HTML5lib
|
||||
module TreeWalkers
|
||||
module REXML
|
||||
class TreeWalker < HTML5lib::TreeWalkers::NonRecursiveTreeWalker
|
||||
|
||||
def node_details(node)
|
||||
case node
|
||||
when ::REXML::Document
|
||||
[:DOCUMENT]
|
||||
when ::REXML::Element
|
||||
if !node.name
|
||||
[:DOCUMENT_FRAGMENT]
|
||||
else
|
||||
[:ELEMENT, node.name,
|
||||
node.attributes.map {|name,value| [name,value]},
|
||||
node.has_elements? || node.has_text?]
|
||||
end
|
||||
when ::REXML::Text
|
||||
[:TEXT, node.value]
|
||||
when ::REXML::Comment
|
||||
[:COMMENT, node.string]
|
||||
when ::REXML::DocType
|
||||
[:DOCTYPE, node.name]
|
||||
when ::REXML::XMLDecl
|
||||
[nil]
|
||||
else
|
||||
[:UNKNOWN, node.class.inspect]
|
||||
end
|
||||
end
|
||||
|
||||
def first_child(node)
|
||||
node.children.first
|
||||
end
|
||||
|
||||
def next_sibling(node)
|
||||
node.next_sibling
|
||||
end
|
||||
|
||||
def parent(node)
|
||||
node.parent
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
48
vendor/plugins/HTML5lib/lib/html5lib/treewalkers/simpletree.rb
vendored
Normal file
48
vendor/plugins/HTML5lib/lib/html5lib/treewalkers/simpletree.rb
vendored
Normal file
|
|
@ -0,0 +1,48 @@
|
|||
require 'html5lib/treewalkers/base'
|
||||
|
||||
module HTML5lib
|
||||
module TreeWalkers
|
||||
module SimpleTree
|
||||
class TreeWalker < HTML5lib::TreeWalkers::Base
|
||||
include HTML5lib::TreeBuilders::SimpleTree
|
||||
|
||||
def walk(node)
|
||||
case node
|
||||
when Document, DocumentFragment
|
||||
return
|
||||
|
||||
when DocumentType
|
||||
yield doctype(node.name)
|
||||
|
||||
when TextNode
|
||||
text(node.value) {|token| yield token}
|
||||
|
||||
when Element
|
||||
if VOID_ELEMENTS.include?(node.name)
|
||||
yield emptyTag(node.name, node.attributes, node.hasContent())
|
||||
else
|
||||
yield startTag(node.name, node.attributes)
|
||||
for child in node.childNodes
|
||||
walk(child) {|token| yield token}
|
||||
end
|
||||
yield endTag(node.name)
|
||||
end
|
||||
|
||||
when CommentNode
|
||||
yield comment(node.value)
|
||||
|
||||
else
|
||||
puts '?'
|
||||
yield unknown(node.class)
|
||||
end
|
||||
end
|
||||
|
||||
def each
|
||||
for child in @tree.childNodes
|
||||
walk(child) {|node| yield node}
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
Loading…
Add table
Add a link
Reference in a new issue