unnormalize( string, doctype=nil, filter=nil, illegal=nil )
public
Unescapes all possible entities
Show source
def Text::unnormalize( string, doctype=nil, filter=nil, illegal=nil )
rv = string.clone
rv.gsub!( /\r\n?/, "\n" )
matches = rv.scan( REFERENCE )
return rv if matches.size == 0
rv.gsub!( NUMERICENTITY ) {|m|
m=$1
m = "0#{m}" if m[0] == ?x
[Integer(m)].pack('U*')
}
matches.collect!{|x|x[0]}.compact!
if matches.size > 0
if doctype
matches.each do |entity_reference|
unless filter and filter.include?(entity_reference)
entity_value = doctype.entity( entity_reference )
re = /&#{entity_reference};/
rv.gsub!( re, entity_value ) if entity_value
end
end
else
matches.each do |entity_reference|
unless filter and filter.include?(entity_reference)
entity_value = DocType::DEFAULT_ENTITIES[ entity_reference ]
re = /&#{entity_reference};/
rv.gsub!( re, entity_value.value ) if entity_value
end
end
end
rv.gsub!( /&/, '&' )
end
rv
end